feat: 添加视频重复检测功能，支持Redis存储视频键

dailymotion_status_monitor.py

@@ -1,38 +0,0 @@
-from DB import DBVidcon
-import requests
-from logger import logger
-db = DBVidcon()
-
-
-def check_video_removed(video_id):
-    url = f"https://api.dailymotion.com/video/{video_id}"
-    params = {"fields": "published,private,status"}
-    resp = requests.get(url, params=params, timeout=10)
-
-    # 404 -> 不存在或已被删除
-    if resp.status_code == 404:
-        return 1
-
-    data = resp.json()
-    # published=False 或 private=True 都视作“已下架”
-    if not data.get("published", False) or data.get("private", False):
-        return 1
-
-    return 0
-
-
-def main():
-    lis = db.getreport_video()
-    for li in lis:
-        video_id = li['v_xid']
-        status = check_video_removed(video_id)
-        if status == 1:
-            db.mark_video_removed(li['id'], status)
-            logger.info(f"视频id {video_id} 下架")
-        else:
-            db.mark_video_removed(li['id'], status)
-            logger.info(f"视频id {video_id} 仍然存在")
-
-
-if __name__ == '__main__':
-    main()

dump_keyword_title.py

@@ -1,6 +1,6 @@
 import json, time
 import argparse
-from DB import DBVidcon
+from DB import DBVidcon, DBSA
 
 def parse_args():
     parser = argparse.ArgumentParser(
@@ -14,8 +14,10 @@ def main():
     args   = parse_args()
     batch  = int(time.time())
     db     = DBVidcon()
-    push   = None
-    empty  = None
+
+    for chunk in DBSA.stream_video_keys(chunk_size=10_000):
+        db.cache_video_keys_bulk(chunk)
+        print(f"同步Redis=={len(chunk)}")
 
     if args.level == 0:
         push = db.push_l0

dump_keyword_web.py

@@ -1,40 +0,0 @@
-import json, time
-import argparse
-from DB import DBVidcon
-
-def parse_args():
-    parser = argparse.ArgumentParser(
-        description="Dump keyword/title rows into Redis list."
-    )
-    parser.add_argument("-l", "--level", type=int, default=99,
-                        help="value for t.level (default: 99)")
-    return parser.parse_args()
-
-def main():
-    batch  = int(time.time())
-    db     = DBVidcon()
-    push = db.push_web
-    empty = db.web_empty
-
-    if empty():
-        rows = db.fetch_keyword_title(level=0)
-        payload_list = []
-        for row in rows:
-            payload_list.append(json.dumps({**row, "batch": batch}, ensure_ascii=False))
-            if len(payload_list) >= 10000:
-                push(payload_list)
-                payload_list.clear()
-        if payload_list:          # 收尾
-            push(payload_list)
-
-        data = {
-            "level": 0,
-            "batch": batch,
-            "count": len(rows),
-        }
-        db.log_batch_start(data)
-        print(f"✔ 推送 {len(rows)} 行（batch={batch}）到 {push.__name__}队列完毕")
-    db.close()
-
-if __name__ == "__main__":
-    main()

flask_test.py

@@ -1,57 +0,0 @@
-import requests
-from flask import Flask, request, jsonify
-from DB import DBVidcon
-
-app = Flask(__name__)
-
-endpoint = "https://api.dailymotion.com/videos"
-DEFAULT_PAGE = 1
-FIXED_LIMIT = 100
-VALID_SORTS = {
-    'recent', 'relevance', 'alpha', 'alphaaz',
-    'alphaza', 'most', 'least', 'changed'
-}
-
-db = DBVidcon()
-
-@app.route("/get", methods=["GET"])
-def get_videos():
-    keyword = request.args.get("keyword", "").strip()
-    if not keyword:
-        return jsonify({"status": "error", "msg": "keyword 参数不能为空"}), 400
-
-    # 页码和国家参数
-    i = request.args.get("page", DEFAULT_PAGE, type=int)
-    rn = request.args.get("rn", "US").upper()
-
-    # 排序参数，必须合法
-    sort = request.args.get("sort", "relevance").strip().lower()
-    if sort not in VALID_SORTS:
-        return jsonify({
-            "status": "error",
-            "msg": f"sort 参数非法，可选值: {sorted(VALID_SORTS)}"
-        }), 400
-
-    proxy_string = db.get_proxy(rn)
-    proxies = {"http": proxy_string, "https": proxy_string} if proxy_string else None
-
-    params = {
-        "search": keyword,
-        "fields": "id,title,created_time,thumbnail_240_url,duration,"
-                  "owner.id,owner.screenname,likes_total,views_total",
-        "limit": FIXED_LIMIT,
-        "page": i,
-        "sort": sort
-    }
-
-    try:
-        resp = requests.get(endpoint, params=params, proxies=proxies, timeout=10)
-        resp.raise_for_status()
-        jd = resp.json()
-        return jsonify(jd), 200
-    except requests.exceptions.RequestException as e:
-        return jsonify({"status": "error", "msg": str(e)}), 502
-
-
-if __name__ == "__main__":
-    app.run(host="0.0.0.0", port=8000, debug=False)

is_offline_api.py

@@ -1,51 +0,0 @@
-#!/usr/bin/env python3
-# app.py
-import requests
-from flask import Flask, jsonify, abort
-
-app = Flask(__name__)
-
-
-def check_video_removed(video_id):
-    """
-    调用 Dailymotion API 判断视频是否已下架／删除
-    返回:
-        1 → 已被删除 / 不存在 / 已下架 / 设为私有
-        0 → 正常公开中
-    """
-    url = f"https://api.dailymotion.com/video/{video_id}"
-    params = {"fields": "published,private,status"}
-    try:
-        resp = requests.get(url, params=params, timeout=10)
-    except requests.RequestException as exc:
-        # 网络错误时返回 503，让上游知道需要重试
-        abort(503, description=f"Upstream request failed: {exc}")
-
-    # 404 → 不存在或已被删除
-    if resp.status_code == 404:
-        return 1
-
-    # 其他非 2xx 状态码 → 直接透传给客户端
-    if resp.status_code // 100 != 2:
-        abort(resp.status_code, description=resp.text)
-
-    data = resp.json()
-    # published=False 或 private=True 都视作“已下架”
-    if not data.get("published", False) or data.get("private", False):
-        return 1
-
-    return 0
-
-
-@app.route("/video/<video_id>", methods=["GET"])
-def video_status(video_id):
-    removed = check_video_removed(video_id)
-    return jsonify({"video_id": video_id, "removed": removed})
-
-
-if __name__ == "__main__":
-    # 支持通过环境变量覆盖监听地址和端口
-    import os
-    host = os.getenv("HOST", "0.0.0.0")
-    port = 5100
-    app.run(host=host, port=port, debug=False)

kill_main.sh

@@ -1,18 +0,0 @@
-#!/usr/bin/env bash
-
-# -------- 可按需修改 --------
-TARGET="/opt/ql/DailyMotion/main.py"   # 关键字：精确到脚本路径即可
-SIG="9"                                # 信号；默认 -9，想温和一点改成 15
-# --------------------------------
-
-pids=$(pgrep -f "$TARGET")
-
-if [ -z "$pids" ]; then
-    echo "没有发现正在运行的 $TARGET"
-    exit 0
-fi
-
-echo "即将发送 SIG${SIG:-15} 到进程: $pids"
-kill "-${SIG:-15}" $pids
-
-echo "完成"

main.py

@@ -1,4 +1,3 @@
-#!/opt/ql/daily_com/bin/python3
 import base64
 import traceback
 import argparse
@@ -56,15 +55,15 @@ def format_duration(seconds):
         return "00:00"
 
 
-def get_searchInfo(keyword, level, headers, proxy_name, r=2):
+def get_searchInfo(keyword, level, rn, proxy_name, r=2):
     if r == 2:
         logger.info(f"NET处理->{keyword},\trn->{proxy_name},\tlevel->{level}")
     video_list = []
-    max_page = 3
-    limit = 100
+    max_page = 2
+    limit = 30
     endpoint = 'https://api.dailymotion.com/videos'
     if level == 0 or level == 1:
-        max_page = 4
+        max_page = 3
         limit = 100
     for j in range(1, max_page):
         params = {
@@ -88,7 +87,7 @@ def get_searchInfo(keyword, level, headers, proxy_name, r=2):
                 logger.exception(f"[Requested] 未知:{e}, keyword: {keyword}, l: {level}")
             else:
                 time.sleep((3 - r) * 5)
-                return get_searchInfo(keyword, level, headers, proxy_name, r - 1)
+                return get_searchInfo(keyword, level, rn, proxy_name, r - 1)
         try:
             resinfo = jsondata.get("list")
         except Exception:
@@ -98,7 +97,7 @@ def get_searchInfo(keyword, level, headers, proxy_name, r=2):
                 return None
             else:
                 time.sleep((3 - r) * 5)
-                return get_searchInfo(keyword, level, headers, proxy_name, r - 1)
+                return get_searchInfo(keyword, level, rn, proxy_name, r - 1)
         for index, iteminfo in enumerate(resinfo):
             calculated_index = index + 1 + (j - 1) * limit
             xid = iteminfo["id"]
@@ -106,6 +105,10 @@ def get_searchInfo(keyword, level, headers, proxy_name, r=2):
             uxid = iteminfo["owner.id"]
             uid = base64.b64encode(f"Channel:{uxid}".encode('utf-8')).decode('utf-8')
             duration = iteminfo.get('duration')
+            is_repeat = 0
+            if db.video_key_exists(vid.strip(), rn):
+                is_repeat = 1
+
             if duration <= 300:
                 continue
             v_data = {
@@ -123,9 +126,11 @@ def get_searchInfo(keyword, level, headers, proxy_name, r=2):
                 "u_id": uid,
                 "u_xid": uxid,
                 "u_name": iteminfo.get('owner.screenname'),
-                "u_pic": iteminfo.get('owner.avatar_60_url')
+                "u_pic": iteminfo.get('owner.avatar_60_url'),
+                "is_repeat": is_repeat,
             }
             video_list.append(v_data)
+        time.sleep(3)
         if len(video_list) < 100:
             break
     return video_list
@@ -137,11 +142,11 @@ proxiesdict = db.get_proxy_agent_dict()
 def search_worker(payload, kitem, flag):
     try:
         gproxies = proxiesdict[kitem['rn']]
-        v_list = get_searchInfo(kitem['keyword'], kitem['level'], None, gproxies)
+        v_list = get_searchInfo(kitem['keyword'], kitem['level'], kitem['rn'], gproxies)
         if not v_list:
             for i in range(2):
                 time.sleep(i * 5)
-                v_list = get_searchInfo(kitem['keyword'], kitem['level'], None, gproxies)
+                v_list = get_searchInfo(kitem['keyword'], kitem['level'], kitem['rn'], gproxies)
                 if v_list:
                     break
                 time.sleep(2)
@@ -163,11 +168,10 @@ def integrate_data_parallel():
             time.sleep(10)
             continue
 
-        futures = []
-        for payload, kitem in tasks:
-            futures.append(executor.submit(search_worker, payload, kitem, flag))
-            time.sleep(1)
-
+        futures = [
+            executor.submit(search_worker, payload, kitem, flag)
+            for payload, kitem in tasks
+        ]
         rollback = {0: [], 1: [], 2: []}
 
         for fut in concurrent.futures.as_completed(futures):
@@ -178,8 +182,6 @@ def integrate_data_parallel():
                 continue
 
             for item in v_list:
-                if not v_list:
-                    continue
                 DBSA.upsert_video({
                     "keyword": kitem["keyword"],
                     "v_name": kitem["v_name"],
@@ -202,6 +204,7 @@ def integrate_data_parallel():
                     "batch": kitem["batch"],
                     "machine_id": MACHINE_ID,
                     "level": kitem["level"],
+                    "is_repeat": item['is_repeat']
                 })
             DBSA.flush()
         if rollback[0]:
@@ -210,6 +213,7 @@ def integrate_data_parallel():
             db.rollback_l1(rollback[1])
         if rollback[2]:
             db.rollback_l2(rollback[2])
+        time.sleep(10)
 
 
 def parse_args() -> argparse.Namespace:

mysql_to_xlsx.py

@@ -98,9 +98,9 @@ def fetch_all_data_for_rn(rn: str, batches: list[int]) -> pd.DataFrame:
 
 def export_all():
     # 指定要处理的批次
-    batches = [1748965168, 1749049335]
+    batches = [1747324254, 1747323990]
     # 先更新 is_repeat
-    # update_is_repeat(batches)
+    update_is_repeat(batches)
 
     rn_list = get_rn_list()
     timestamp = datetime.now().strftime("%Y%m%d")

oneget.py

@@ -1,684 +0,0 @@
-import argparse
-import base64
-from datetime import datetime
-import concurrent.futures
-import requests
-import uuid
-import random
-import time
-import copy
-from threading import Lock
-from DB import DBVidcon, DBSA
-import json
-from requests.adapters import HTTPAdapter
-from urllib3.util.retry import Retry
-from dateutil import parser as date_parser
-
-MACHINE_ID = 0
-db = DBVidcon()
-proxiesdict = db.get_proxy_agent_dict()
-
-
-class RetryRequests:
-    def __init__(
-            self,
-            proxies: dict = None,
-            timeout: int = 10,
-            total: int = 3,
-            backoff_factor: float = 1.0,
-            status_forcelist: tuple = (500, 502, 503, 504),
-            allowed_methods: tuple = ("GET", "POST"),
-    ):
-        self.session = requests.Session()
-        self.timeout = timeout
-        self.proxies = proxies
-
-        retry = Retry(
-            total=total,
-            backoff_factor=backoff_factor,
-            status_forcelist=status_forcelist,
-            allowed_methods=allowed_methods,
-            raise_on_status=False
-        )
-        adapter = HTTPAdapter(max_retries=retry)
-        self.session.mount("http://", adapter)
-        self.session.mount("https://", adapter)
-
-    def get(self, url, **kwargs):
-        kwargs.setdefault("timeout", self.timeout)
-        if self.proxies:
-            kwargs.setdefault("proxies", self.proxies)
-        return self.session.get(url, **kwargs)
-
-    def post(self, url, **kwargs):
-        kwargs.setdefault("timeout", self.timeout)
-        if self.proxies:
-            kwargs.setdefault("proxies", self.proxies)
-        return self.session.post(url, **kwargs)
-
-
-req = RetryRequests()
-
-
-def clean_dash_to_zero(val):
-    if val in ('-', '', None):
-        return 0
-    try:
-        return int(val)
-    except (ValueError, TypeError) as e:
-        print(f"[字段异常] val = {val} → {str(e)}")
-        return 0
-
-
-def format_create_time(timestr):
-    try:
-        dt = date_parser.isoparse(timestr)
-        return dt.strftime("%Y-%m-%d %H:%M:%S")
-    except Exception as e:
-        print(f"[时间格式错误] {timestr} → {str(e)}")
-        return "1970-01-01 00:00:00"
-
-
-def format_duration(seconds):
-    try:
-        seconds = int(seconds)
-        return f"{seconds // 60:02}:{seconds % 60:02}"
-    except Exception:
-        return "00:00"
-
-
-class DMHeaderManager:
-    _headers_template = {
-        'Accept': '*/*, */*',
-        'Cache-Control': 'no-cache',
-        'Connection': 'keep-alive',
-        'Content-Type': 'application/json, application/json',
-        'Host': 'graphql.api.dailymotion.com',
-        'Origin': 'https://www.dailymotion.com',
-        'Referer': 'https://www.dailymotion.com/',
-        'Sec-Fetch-Dest': 'empty',
-        'Sec-Fetch-Mode': 'cors',
-        'Sec-Fetch-Site': 'same-site',
-        'User-Agent': 'Mozilla/5.0',
-        'X-DM-AppInfo-Id': 'com.dailymotion.neon',
-        'X-DM-AppInfo-Type': 'website',
-        'X-DM-AppInfo-Version': 'v2025-05-26T13:45:05.666Z',
-        'X-DM-Neon-SSR': '0',
-        'X-DM-Preferred-Country': 'tw',
-        'accept-language': 'zh-CN',
-        'authorization': '',
-        'sec-ch-ua': '"Chromium";v="128", "Not;A=Brand";v="24", "Google Chrome";v="128"',
-        'sec-ch-ua-mobile': '?0',
-        'sec-ch-ua-platform': '"Windows"',
-        'x-dm-visit-id': '',
-        'x-dm-visitor-id': '',
-    }
-
-    _user_agents = [
-        'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
-        'Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
-        'Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11',
-        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)',
-        'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/136.0.0.0 Safari/537.36',
-        'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36',
-    ]
-
-    def __init__(self, proxies: dict = None):
-        self._headers_cache = None
-        self._cache_lock = Lock()
-        self._proxies = proxies
-
-    def get_headers(self, retry: int = 2) -> dict:
-        visitor_id = str(uuid.uuid4())
-        visit_id = str(int(time.time() * 1000))
-        traffic_segment = str(random.randint(100_000, 999_999))
-        ua = random.choice(self._user_agents)
-
-        token_headers = {
-            'Accept': '*/*',
-            'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
-            'Cache-Control': 'no-cache',
-            'Connection': 'keep-alive',
-            'Content-Type': 'application/x-www-form-urlencoded',
-            'Origin': 'https://www.dailymotion.com',
-            'Pragma': 'no-cache',
-            'Referer': 'https://www.dailymotion.com/',
-            'Sec-Fetch-Dest': 'empty',
-            'Sec-Fetch-Mode': 'cors',
-            'Sec-Fetch-Site': 'same-site',
-            'User-Agent': ua,
-            'sec-ch-ua': '"Chromium";v="136", "Google Chrome";v="136", "Not.A/Brand";v="99"',
-            'sec-ch-ua-mobile': '?0',
-            'sec-ch-ua-platform': '"Windows"',
-        }
-
-        data = {
-            'client_id': 'f1a362d288c1b98099c7',
-            'client_secret': 'eea605b96e01c796ff369935357eca920c5da4c5',
-            'grant_type': 'client_credentials',
-            'traffic_segment': traffic_segment,
-            'visitor_id': visitor_id,
-        }
-
-        response = req.post(
-            'https://graphql.api.dailymotion.com/oauth/token',
-            headers=token_headers,
-            data=data,
-            proxies=self._proxies,
-            timeout=10
-        )
-        response.raise_for_status()
-        token = response.json()['access_token']
-
-        new_headers = copy.deepcopy(self._headers_template)
-        new_headers['authorization'] = f'Bearer {token}'
-        new_headers['x-dm-visit-id'] = visit_id
-        new_headers['x-dm-visitor-id'] = visitor_id
-        new_headers['User-Agent'] = ua
-
-        with self._cache_lock:
-            self._headers_cache = copy.deepcopy(new_headers)
-
-        return new_headers
-
-
-class DMVideoInfo:
-    def __init__(self, proxies: dict = None, max_retries: int = 3, backoff_factor: float = 0.5):
-        self.proxies = proxies
-        self.max_retries = max_retries
-        self.backoff_factor = backoff_factor
-
-    def get_video_info(self, data: dict) -> dict:
-        v_xid = data.get('v_xid')
-        url = f'https://api.dailymotion.com/video/{v_xid}'
-        params = {
-            'fields': 'id,title,created_time,thumbnail_240_url,duration,'
-                      'owner.id,owner.screenname,likes_total,views_total,'
-                      'owner.avatar_60_url,owner.followers_total,owner.videos_total'
-        }
-
-        try:
-            resp = req.get(url, params=params, timeout=10)
-            resp.raise_for_status()
-            r_data = resp.json()
-            xid = r_data["id"]
-            vid = base64.b64encode(f"Video:{xid}".encode('utf-8')).decode('utf-8')
-            uxid = r_data["owner.id"]
-            uid = base64.b64encode(f"Channel:{uxid}".encode('utf-8')).decode('utf-8')
-            duration = r_data.get("duration", 0)
-            if duration < 30:
-                return None
-            data["v_id"] = vid
-            data["title"] = r_data.get("title", "")
-            data["link"] = "https://www.dailymotion.com/video/" + xid
-            data["duration"] = format_duration(r_data.get("duration", 0))
-            data['create_time'] = format(
-                datetime.fromtimestamp(r_data.get("created_time")).strftime("%Y-%m-%d %H:%M:%S"))
-            data['fans'] = clean_dash_to_zero(r_data.get("owner.followers_total", 0))
-            data['videos'] = clean_dash_to_zero(r_data.get("owner.videos_total", 0))
-            data['watch_number'] = clean_dash_to_zero(r_data.get("views_total", 0))
-            data['cover_pic'] = r_data.get('thumbnail_240_url')
-            data['u_id'] = uid
-            data['u_xid'] = uxid
-            data['u_name'] = r_data.get("owner.screenname", "")
-            data['u_pic'] = r_data.get("owner.avatar_60_url", "")
-            DBSA.upsert_video(data)
-            DBSA.flush()
-        except requests.RequestException as e:
-            print(f"[ERROR] 请求失败 vxid={v_xid} : {e}")
-            return None
-
-
-def parse_args() -> argparse.Namespace:
-    global MACHINE_ID
-    parser = argparse.ArgumentParser(
-        description="Configure worker settings."
-    )
-    parser.add_argument(
-        "-m", "--machine-id",
-        type=int,
-        help=f"Machine identifier (default: {MACHINE_ID})"
-    )
-
-    args = parser.parse_args()
-
-    if args.machine_id is not None:
-        MACHINE_ID = args.machine_id
-
-    if MACHINE_ID is None or MACHINE_ID == 0:
-        raise ValueError("请指定机器编号")
-    return args
-
-
-def main():
-    while True:
-        kwdata = db.get_web_items()
-        if not kwdata:
-            print("没有获取到关键词数据")
-            time.sleep(30)
-            continue
-        print(f"搜索关键词数据: {kwdata}")
-        kwdata = kwdata[0][1]
-        rn = kwdata['rn']
-        proxy_name = proxiesdict.get(rn)
-        # proxies_str = "http://127.0.0.1:10808"
-        proxies_str = db.get_proxy(proxy_name, '-1')
-        proxies = {
-            'http': proxies_str,
-            'https': proxies_str
-        }
-        kw = kwdata['keyword']
-        dmheader_manager = DMHeaderManager(proxies=proxies)
-        dmvideo_info = DMVideoInfo(proxies=proxies)
-        headers = dmheader_manager.get_headers()
-        for i in range(1, 11):
-            data = {
-                "operationName": "SEARCH_QUERY",
-                "variables": {
-                    "query": kw,
-                    "shouldIncludeTopResults": True,  # 是否包含热门结果
-                    "shouldIncludeChannels": False,  # 是否包含频道
-                    "shouldIncludePlaylists": False,  # 是否包含播放列表
-                    "shouldIncludeHashtags": False,  # 是否包含标签
-                    "shouldIncludeVideos": False,  # 是否包含视频
-                    "shouldIncludeLives": False,  # 是否包含直播
-                    "page": i,
-                    "limit": 20,
-                    "recaptchaToken": None
-                },
-                "query": """
-            fragment VIDEO_BASE_FRAGMENT on Video {
-              id
-              xid
-              title
-              createdAt
-              duration
-              aspectRatio
-              thumbnail(height: PORTRAIT_240) {
-                id
-                url
-                __typename
-              }
-              creator {
-                id
-                xid
-                name
-                displayName
-                accountType
-                avatar(height: SQUARE_60) {
-                  id
-                  url
-                  __typename
-                }
-                __typename
-              }
-              __typename
-            }
-            
-            fragment CHANNEL_BASE_FRAG on Channel {
-              id
-              xid
-              name
-              displayName
-              accountType
-              isFollowed
-              avatar(height: SQUARE_120) {
-                id
-                url
-                __typename
-              }
-              followerEngagement {
-                id
-                followDate
-                __typename
-              }
-              metrics {
-                id
-                engagement {
-                  id
-                  followers {
-                    edges {
-                      node {
-                        id
-                        total
-                        __typename
-                      }
-                      __typename
-                    }
-                    __typename
-                  }
-                  __typename
-                }
-                __typename
-              }
-              __typename
-            }
-            
-            fragment PLAYLIST_BASE_FRAG on Collection {
-              id
-              xid
-              name
-              description
-              thumbnail(height: PORTRAIT_240) {
-                id
-                url
-                __typename
-              }
-              creator {
-                id
-                xid
-                name
-                displayName
-                accountType
-                avatar(height: SQUARE_60) {
-                  id
-                  url
-                  __typename
-                }
-                __typename
-              }
-              metrics {
-                id
-                engagement {
-                  id
-                  videos(filter: {visibility: {eq: PUBLIC}}) {
-                    edges {
-                      node {
-                        id
-                        total
-                        __typename
-                      }
-                      __typename
-                    }
-                    __typename
-                  }
-                  __typename
-                }
-                __typename
-              }
-              __typename
-            }
-            
-            fragment HASHTAG_BASE_FRAG on Hashtag {
-              id
-              xid
-              name
-              metrics {
-                id
-                engagement {
-                  id
-                  videos {
-                    edges {
-                      node {
-                        id
-                        total
-                        __typename
-                      }
-                      __typename
-                    }
-                    __typename
-                  }
-                  __typename
-                }
-                __typename
-              }
-              __typename
-            }
-            
-            fragment LIVE_BASE_FRAGMENT on Live {
-              id
-              xid
-              title
-              audienceCount
-              aspectRatio
-              isOnAir
-              thumbnail(height: PORTRAIT_240) {
-                id
-                url
-                __typename
-              }
-              creator {
-                id
-                xid
-                name
-                displayName
-                accountType
-                avatar(height: SQUARE_60) {
-                  id
-                  url
-                  __typename
-                }
-                __typename
-              }
-              __typename
-            }
-            
-            query SEARCH_QUERY(
-              $query: String!,
-              $shouldIncludeTopResults: Boolean!,
-              $shouldIncludeVideos: Boolean!,
-              $shouldIncludeChannels: Boolean!,
-              $shouldIncludePlaylists: Boolean!,
-              $shouldIncludeHashtags: Boolean!,
-              $shouldIncludeLives: Boolean!,
-              $page: Int,
-              $limit: Int,
-              $sortByVideos: SearchVideoSort,
-              $durationMinVideos: Int,
-              $durationMaxVideos: Int,
-              $createdAfterVideos: DateTime,
-              $recaptchaToken: String
-            ) {
-              search(token: $recaptchaToken) {
-                id
-            
-                stories(query: $query, first: $limit, page: $page) @include(if: $shouldIncludeTopResults) {
-                  metadata {
-                    id
-                    algorithm {
-                      uuid
-                      __typename
-                    }
-                    __typename
-                  }
-                  pageInfo {
-                    hasNextPage
-                    nextPage
-                    __typename
-                  }
-                  edges {
-                    node {
-                      ...VIDEO_BASE_FRAGMENT
-                      ...CHANNEL_BASE_FRAG
-                      ...PLAYLIST_BASE_FRAG
-                      ...HASHTAG_BASE_FRAG
-                      ...LIVE_BASE_FRAGMENT
-                      __typename
-                    }
-                    __typename
-                  }
-                  __typename
-                }
-            
-                videos(
-                  query: $query,
-                  first: $limit,
-                  page: $page,
-                  sort: $sortByVideos,
-                  durationMin: $durationMinVideos,
-                  durationMax: $durationMaxVideos,
-                  createdAfter: $createdAfterVideos
-                ) @include(if: $shouldIncludeVideos) {
-                  metadata {
-                    id
-                    algorithm {
-                      uuid
-                      __typename
-                    }
-                    __typename
-                  }
-                  pageInfo {
-                    hasNextPage
-                    nextPage
-                    __typename
-                  }
-                  edges {
-                    node {
-                      id
-                      ...VIDEO_BASE_FRAGMENT
-                      __typename
-                    }
-                    __typename
-                  }
-                  __typename
-                }
-            
-                lives(query: $query, first: $limit, page: $page) @include(if: $shouldIncludeLives) {
-                  metadata {
-                    id
-                    algorithm {
-                      uuid
-                      __typename
-                    }
-                    __typename
-                  }
-                  pageInfo {
-                    hasNextPage
-                    nextPage
-                    __typename
-                  }
-                  edges {
-                    node {
-                      id
-                      ...LIVE_BASE_FRAGMENT
-                      __typename
-                    }
-                    __typename
-                  }
-                  __typename
-                }
-            
-                channels(query: $query, first: $limit, page: $page) @include(if: $shouldIncludeChannels) {
-                  metadata {
-                    id
-                    algorithm {
-                      uuid
-                      __typename
-                    }
-                    __typename
-                  }
-                  pageInfo {
-                    hasNextPage
-                    nextPage
-                    __typename
-                  }
-                  edges {
-                    node {
-                      id
-                      ...CHANNEL_BASE_FRAG
-                      __typename
-                    }
-                    __typename
-                  }
-                  __typename
-                }
-            
-                playlists: collections(query: $query, first: $limit, page: $page) @include(if: $shouldIncludePlaylists) {
-                  metadata {
-                    id
-                    algorithm {
-                      uuid
-                      __typename
-                    }
-                    __typename
-                  }
-                  pageInfo {
-                    hasNextPage
-                    nextPage
-                    __typename
-                  }
-                  edges {
-                    node {
-                      id
-                      ...PLAYLIST_BASE_FRAG
-                      __typename
-                    }
-                    __typename
-                  }
-                  __typename
-                }
-            
-                hashtags(query: $query, first: $limit, page: $page) @include(if: $shouldIncludeHashtags) {
-                  metadata {
-                    id
-                    algorithm {
-                      uuid
-                      __typename
-                    }
-                    __typename
-                  }
-                  pageInfo {
-                    hasNextPage
-                    nextPage
-                    __typename
-                  }
-                  edges {
-                    node {
-                      id
-                      ...HASHTAG_BASE_FRAG
-                      __typename
-                    }
-                    __typename
-                  }
-                  __typename
-                }
-            
-                __typename
-              }
-            }
-            """
-            }
-
-            payload = json.dumps(data).encode()
-
-            response = req.post('https://graphql.api.dailymotion.com/', headers=headers, data=payload,
-                                proxies=proxies)
-
-            data = response.json()
-            try:
-                edges = data['data']['search']['stories']['edges']
-            except (TypeError,KeyError):
-                print("stories 为 None 或结构异常，跳过")
-                break
-            edges_len = len(edges)
-            print(f"第 {i} 页，关键词: {kw}，获取到 {edges_len} 条数据")
-            tancks = []
-            for j, edge in enumerate(edges):
-                node = edge.get("node", {})
-                s_data = {
-                    "keyword": kw,
-                    "v_name": kwdata.get("v_name", ""),
-                    "v_xid": node.get("xid"),
-                    "batch": kwdata.get("batch"),
-                    "rn": kwdata.get("rn"),
-                    "machine_id": MACHINE_ID,
-                    "index": (i - 1) * 20 + j + 1,
-                    "level": 0,
-                }
-                tancks.append(s_data)
-            with concurrent.futures.ThreadPoolExecutor(max_workers=20) as executor:
-                executor.map(dmvideo_info.get_video_info, tancks)
-            if edges_len < 20:
-                break
-            time.sleep(10)
-
-        time.sleep(20)
-
-if __name__ == '__main__':
-    parse_args()
-    start_time = datetime.now()
-    print(f"开始时间：{start_time.strftime('%Y-%m-%d %H:%M:%S')}")
-    main()
-
-
-

onoe.py

@@ -34,7 +34,19 @@ UserAgent = [
     'User-Agent, Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)',
     'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Maxthon/5.0.3.4000 Chrome/47.0.2526.73 Safari/537.36',
     'User-Agent, Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)']
-
+sec_ch_ua_list = [
+    '"Chromium";v="0", "Not;A=Brand";v="24", "Google Chrome";v="0"',
+    '"Chromium";v="0", "Not;A=Brand";v="24", "Google Chrome";v="0"',
+    '"Chromium";v="0", "Not;A=Brand";v="24", "Google Chrome";v="0"',
+    '"Chromium";v="0", "Not;A=Brand";v="24", "Google Chrome";v="0"',
+    '"Chromium";v="0", "Not;A=Brand";v="24", "Google Chrome";v="0"',
+    '"Chromium";v="136", "Not;A=Brand";v="24", "Google Chrome";v="136"',
+    '"Chromium";v="128", "Not;A=Brand";v="24", "Google Chrome";v="128"',
+    '"Chromium";v="53", "Not;A=Brand";v="24", "Google Chrome";v="53"',
+    '"Chromium";v="0", "Not;A=Brand";v="24", "Google Chrome";v="0"',
+    '"Chromium";v="47", "Not;A=Brand";v="24", "Google Chrome";v="47"',
+    '"Chromium";v="0", "Not;A=Brand";v="24", "Google Chrome";v="0"'
+]
 
 def get_part_ids(part_num: int, take: int, offset: int = 0):
     part_ids = list(range(offset, offset + take))
@@ -221,14 +233,17 @@ def gettoken(proxy, r=2):
     }
     try:
         proxy_str = db.get_proxy(proxy)
+        logger.info(f"[代理] => {proxy_str}")
         url = 'https://graphql.api.dailymotion.com/oauth/token'
         response = requests.post(url, headers=headers, data=data, proxies={"http": proxy_str, "https": proxy_str})
         token = response.json()['access_token']
         copy_headers = copy.deepcopy(headers1)
+        uaidx = random.randint(0, len(UserAgent) - 1)
         copy_headers['authorization'] = "Bearer " + token
         copy_headers['x-dm-visit-id'] = str(int(time.time() * 1000))
         copy_headers['x-dm-visitor-id'] = uuid_with_dash
-        copy_headers['User-Agent'] = UserAgent[random.randint(0, len(UserAgent) - 1)]
+        copy_headers['User-Agent'] = UserAgent[uaidx]
+        copy_headers['sec-ch-ua'] = sec_ch_ua_list[uaidx]
         copy_headers['X-DM-Preferred-Country'] = proxy.lower()
         with _cache_lock:
             _headers_cache = copy_headers
@@ -267,18 +282,18 @@ def solve_recaptcha_v3_with_proxy(
             payload = {
                 "clientKey": "CAP-A76C932D4C6CCB3CA748F77FDC07D996",
                 "task": {
-                    "type": "ReCaptchaV3Task",
+                    "type": "ReCaptchaV3TaskProxyLess",
                     "websiteURL": f"https://www.dailymotion.com/search/{encoded_query}/top-results",
                     "websiteKey": "6LeOJBIrAAAAAPMIjyYvo-eN_9W1HDOkrEqHR8tM",
-                    "pageAction": "___grecaptcha_cfg.clients['100000']['L']['L']['promise-callback'](gRecaptchaResponse)",
+                    "pageAction": "search",
                     "minScore": 0.5
                 }
             }
-            resp = requests.post(create_url, json=payload, headers=headers, timeout=30)
+            resp = requests.post(create_url, data=json.dumps(payload), headers=headers, timeout=30)
             logger.info(f"[token] 发送 payload:{payload}")
             resp.raise_for_status()
             task_id = resp.json()["taskId"]
-            logger.info(f"task_id: {task_id}")
+            logger.info(f"task_id: {resp.text}")
             # 轮询获取结果
             check_payload = {"clientKey": "CAP-A76C932D4C6CCB3CA748F77FDC07D996", "taskId": task_id}
             for i in range(max_poll_attempts):
@@ -287,7 +302,7 @@ def solve_recaptcha_v3_with_proxy(
                 result = r.json()
                 logger.info(f"第{i}次,task_id:{task_id},结果:{result}")
                 if result.get("status") == "ready":
-                    return result["solution"]["token"]
+                    return result["solution"]["gRecaptchaResponse"]
                 time.sleep(polling_interval)
 
             raise TimeoutError(f"任务 {task_id} 在轮询 {max_poll_attempts} 次后未完成")

participle.py

@@ -1,56 +0,0 @@
-import requests
-
-url = "https://api.siliconflow.cn/v1/chat/completions"
-kw = "朝雪录"
-rn = "US"
-payload = {
-    "model": "Qwen/Qwen3-14B",
-    "max_tokens": 512,
-    "enable_thinking": True,
-    "thinking_budget": 4096,
-    "min_p": 0.05,
-    "temperature": 0.7,
-    "top_p": 0.7,
-    "top_k": 50,
-    "frequency_penalty": 0.5,
-    "n": 1,
-    "stream": False,
-    "stop": [],
-    "messages": [
-        {
-            "role": "user",
-            "content": """你是一个视频搜索优化助手。用户给你一个中文视频标题或关键词，请你翻译并联想出 10 个适合用于英文视频网站（如 Dailymotion）搜索的关键词，结果用英文逗号分隔输出，仅返回关键词列表，不加说明。
-
-示例输入：朝雪录
-示例输出：Coroner's Diary,Coroners Diary, Coroners Diary episode,Coroners Diary season 1,Coroners Diary full episode,coroners diary
-"""
-        },
-        {
-            "role": "user",
-            "content": f"请推理：{kw} 并输出 10 个地区缩写为{rn}的适合用于视频网站搜索的关键词,地区缩写不在关键词内,。"
-        }
-    ]
-}
-
-headers = {
-    "Authorization": "Bearer sk-isvydeloxqhoiwoiojleghdsuhagryjbxzphfhxneevxeoeh",
-    "Content-Type": "application/json"
-}
-
-response = requests.post(url, json=payload, headers=headers, timeout=30)
-
-def parse_keywords_from_response(resp_json):
-    try:
-        # 取出文本内容
-        content = resp_json["choices"][0]["message"]["content"]
-        # 按英文逗号分隔
-        keywords = [kw.strip() for kw in content.split(",") if kw.strip()]
-        return keywords
-    except Exception as e:
-        print("解析失败:", e)
-        return []
-
-kws = parse_keywords_from_response(response.json())
-
-print(kws)
-print(len(kws))

push_report_to_redis.py

@@ -1,19 +0,0 @@
-import json
-from DB import DBVidcon
-payload_list = []
-db = DBVidcon()
-rows = db.get_report_video()
-push  = db.push_report
-
-# =======================
-
-for row in rows:
-    payload_list.append(json.dumps({**row}, ensure_ascii=False))
-    if len(payload_list) >= 10000:
-        push(payload_list)
-        payload_list.clear()
-if payload_list:  # 收尾
-    push(payload_list)
-
-db.close()
-

report.py

@@ -1,124 +0,0 @@
-import argparse
-import json
-import time
-from DB import DBVidcon, DBSA
-from report_video import DailymotionClient
-from logger import logger
-import requests
-
-MACHINE_ID = None
-IsSubsequent = False
-
-
-def parse_args() -> argparse.Namespace:
-    global MACHINE_ID, IsSubsequent
-
-    parser = argparse.ArgumentParser(
-        description="Configure worker settings."
-    )
-    parser.add_argument(
-        "-m", "--machine-id",
-        type=int,
-        help=f"Machine identifier (default: {MACHINE_ID})"
-    )
-    parser.add_argument(
-        "-s", "--IsSubsequent",
-        type=int,
-        help=f"Maximum concurrent workers (default: {IsSubsequent})"
-    )
-
-    args = parser.parse_args()
-
-    if args.machine_id is not None:
-        MACHINE_ID = args.machine_id
-
-    if args.IsSubsequent is not None:
-        if args.IsSubsequent <= 0:
-            IsSubsequent = False
-        else:
-            IsSubsequent = True
-    if MACHINE_ID is None:
-        raise ValueError("请指定机器编号")
-    return args
-
-
-parse_args()
-
-
-def get_public_ip():
-    try:
-        response = requests.get("https://api.ipify.org?format=json", timeout=5)
-        return response.json().get("ip")
-    except requests.RequestException as e:
-        print("获取失败:", e)
-        return None
-
-
-ip = get_public_ip()
-logger.info(f"当前机器IP: {ip}, 机器编号: {MACHINE_ID}, 是否后续处理: {IsSubsequent}")
-db = DBVidcon()
-
-account = db.get_account_info(MACHINE_ID)
-
-d = DailymotionClient(email=account['account'], password=account['password'])
-
-k = {
-    "open": 1,
-    "solved": 2,
-    "awaiting your reply": 3,
-}
-
-last_main_run = 0
-last_subsequent_run = 0
-
-MAIN_INTERVAL = 60 * 60  # 每 5 分钟执行一次
-SUBSEQUENT_INTERVAL = 30 * 60  # 每 60 分钟执行一次
-
-# d.test()
-
-while True:
-    now = int(time.time())
-
-    # 处理主流程
-    if now - last_main_run >= MAIN_INTERVAL:
-        last_main_run = now
-        re_list = []
-        idss = []
-        lis = db.item_report(100)
-        if len(lis) > 0:
-            for li in lis:
-                item = json.loads(li[0])
-                re_list.append(item)
-                idss.append(item['id'])
-                logger.info(f"name:{item['name_title']},link:{item['link']} ")
-            try:
-                ids, info, report_id, status, report_ts = d.process_ticket(re_list)
-                subsequent_status = k.get(status, 1)
-                db.update_fight_record_status(
-                    ids, report_id, 2, f"http://{ip}:5000/image/{info}",
-                    report_ts, subsequent_status, MACHINE_ID
-                )
-                db.flush()
-            except Exception as e:
-                logger.error(f"ID:{re_list[0]['id']}, end id{re_list[-1]['id']}, e:{e}")
-                db.update_fight_record_status(idss, 0, 3, str(e), mid=MACHINE_ID)
-                time.sleep(60)  # 出错延迟
-
-    if now - last_subsequent_run >= SUBSEQUENT_INTERVAL and IsSubsequent:
-        last_subsequent_run = now
-        subsequent_list = db.get_subsequent_report_video(MACHINE_ID)
-        if len(subsequent_list) > 0:
-            for li in subsequent_list:
-                subsequent_status = 0
-                r_id = li['report_id']
-                logger.info(f"subsequent report_id:{r_id} ")
-                # try:
-                subsequent_status, info = d.report_follow_up(r_id)
-                db.update_subsequent_status_by_report_id(
-                    r_id, subsequent_status, f"http://{ip}:5000/image/{info}"
-                )
-                # except Exception as e:
-                #     logger.logger.error(f"ID:{rs_id}, e:{e}")
-                #     db.update_subsequent_status_by_id(rs_id, 1, str(e))
-                time.sleep(5)  # 避免频繁请求
-    time.sleep(5)

report_video.py

@@ -1,417 +0,0 @@
-import time
-import functools
-import os
-import re
-from datetime import datetime
-from sys import platform
-import requests
-from logger import logger
-from playwright.sync_api import (
-    sync_playwright,
-    TimeoutError as PlaywrightTimeoutError,
-    Page,
-    Browser,
-)
-
-
-def solve_turnstile_capsolver(page: Page,
-                              timeout: int = 120) -> bool:
-    """
-    使用 CapSolver 自动完成当前 Page 上的 Cloudflare Turnstile。
-    成功返回 True，失败/超时返回 False。
-    """
-    cap_key = "CAP-A76C932D4C6CCB3CA748F77FDC07D996"
-    widget = page.query_selector("div.cf-turnstile[data-sitekey]")
-    if not widget:
-        return False
-    sitekey = widget.get_attribute("data-sitekey")
-    page_url = page.url
-
-    create_payload = {
-        "clientKey": cap_key,
-        "task": {
-            "type": "TurnstileTaskProxyLess",
-            "websiteURL": page_url,
-            "websiteKey": sitekey
-        }
-    }
-    create_resp = requests.post(
-        "https://api.capsolver.com/createTask",
-        json=create_payload, timeout=20
-    ).json()
-    if create_resp.get("errorId"):
-        print("[CapSolver] createTask 失败:", create_resp)
-        return False
-    task_id = create_resp["taskId"]
-
-    poll_payload = {"clientKey": cap_key, "taskId": task_id}
-    token = None
-    elapsed, step = 0, 3
-    while elapsed < timeout:
-        time.sleep(step)
-        elapsed += step
-        res = requests.post(
-            "https://api.capsolver.com/getTaskResult",
-            json=poll_payload, timeout=15
-        ).json()
-        if res.get("status") == "ready":
-            token = res["solution"]["token"]
-            break
-        if res.get("status") != "processing":
-            print("[CapSolver] getTaskResult 异常:", res)
-            return False
-
-    if not token:
-        print("[CapSolver] 超时未取到 token")
-        return False
-
-    page.evaluate(
-        """(tk) => {
-            const ta = document.querySelector('textarea[name="cf-turnstile-response"]');
-            if (ta) ta.value = tk;
-            if (window.turnstileCallback)
-                try { window.turnstileCallback(tk); } catch(e){}
-        }""",
-        token
-    )
-    page.wait_for_timeout(1500)
-    return True
-
-
-def require_login(func):
-    @functools.wraps(func)
-    def wrapper(self, *args, **kwargs):
-        self.ensure_login()
-        return func(self, *args, **kwargs)
-
-    return wrapper
-
-
-class DailymotionClient:
-    url = "https://faq.dailymotion.com/hc/en-us/requests/new"
-    EMAIL = "copyright@qiyi.com"
-    PASSWORD = "ppsIQIYI2018@"
-
-    def __init__(self,email, password, headless: bool = None):
-        self.email = email
-        self.password = password
-        self.headless = headless
-        self.check_interval = 60 * 60
-        if self.headless is None:
-            self.headless = platform == "linux" or platform == "linux2"
-
-        if self.headless:
-            proxy = None
-            self.file_path = "/opt/ql/DailyMotion/oss/LOA.pdf"
-            self.file_path2 = "/opt/ql/DailyMotion/oss/BAZTSJT.pdf"
-        else:
-            proxy={'server': 'http://127.0.0.1:7890'}
-            self.file_path = "./oss/LOA.pdf"
-            self.file_path2 = "./oss/BAZTSJT.pdf"
-        logger.info(f"Launching DailymotionClient with headless={self.headless}, proxy={proxy}")
-        self._pw = sync_playwright().start()
-        self.browser: Browser = self._pw.chromium.launch(
-            headless=self.headless,
-            proxy=proxy,
-        )
-        self.context = self.browser.new_context(
-            user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
-                       "AppleWebKit/537.36 (KHTML, like Gecko) "
-                       "Chrome/122.0.0.0 Safari/537.36",
-            locale="en-US",
-            viewport={"width": 1280, "height": 800},
-            timezone_id="Asia/Shanghai",
-            permissions=[],
-        )
-        self.context.add_init_script("Object.defineProperty(navigator, 'webdriver', {get: () => undefined})")
-        self.page: Page = self.context.new_page()
-
-        self._last_check_ts = 0
-        self._last_check_result = False
-        os.makedirs('screenshots', exist_ok=True)
-        self.page.goto(self.url)
-
-    def _do_login(self) -> None:
-        self.page.goto(self.url, timeout=30000)
-        # self.page.wait_for_load_state("networkidle", timeout=30000)
-        self.page.wait_for_timeout(3000)
-
-        file_path = f'screenshots/{str(int(time.time()))}.png'
-        self.page.screenshot(path=file_path)
-
-        if self.page.query_selector("div.cf-turnstile[data-sitekey]"):
-            ok = solve_turnstile_capsolver(self.page)
-            if not ok:
-                raise RuntimeError("CapSolver 处理 Turnstile 失败")
-
-        logbtn = self.page.locator("//a[@class='login button']")
-        if logbtn.count() > 0:
-            logbtn.nth(0).click()
-
-        self.page.wait_for_selector("//input[@data-testid=\"emailInput\"]")
-
-        # “我了解”弹窗
-        i_now_btn = self.page.locator("button:has-text(\"I understand\")")
-        if i_now_btn.count() > 0:
-            i_now_btn.click()
-
-        # 输入账号密码
-        email_edit = self.page.locator("//input[@data-testid=\"emailInput\"]")
-        password_edit = self.page.locator("//input[@data-testid=\"passwordInput\"]")
-        if email_edit.count():
-            email_edit.fill(self.email)
-        if password_edit.count():
-            password_edit.fill(self.password)
-
-        # 登录
-        login_btn = self.page.locator('button[form="signin-form"][type="submit"]')
-        try:
-            self.page.wait_for_selector(
-                'button[form="signin-form"][type="submit"]:not([disabled])', timeout=20000
-            )
-        except PlaywrightTimeoutError:
-            pass
-        login_btn.click()
-
-        # 等待跳回
-        self.page.wait_for_url(self.url, timeout=30000)
-        time.sleep(1)
-        self._last_check_ts = time.time()
-        self._last_check_result = True
-
-    def _detect_login(self) -> bool:
-        self.page.goto(self.url, timeout=30000)
-        self.page.wait_for_timeout(3000)
-        return self.page.locator("//a[@class='login button']").count() == 0
-
-    def is_logged_in(self) -> bool:
-        now = time.time()
-        if now - self._last_check_ts < self.check_interval:
-            return self._last_check_result
-
-        try:
-            ok = self._detect_login()
-        except Exception:
-            ok = False
-
-        self._last_check_ts = now
-        self._last_check_result = ok
-        return ok
-
-    def ensure_login(self) -> None:
-        if not self.is_logged_in():
-            self._do_login()
-
-    @require_login
-    def process_ticket(self, lis: list):
-
-        titles = "\r\n"
-        links = ""
-        ids= []
-        title = ""
-        link = ""
-        assignment = True
-        for li in lis:
-            if assignment:
-                title = li['name_title']
-                link = li['link']
-                assignment = False
-            ids.append(li['id'])
-            titles += li['name_title'] + ",\r\n"
-            links += li['link'] + ",\r\n"
-        logger.info(f"Processing ticket for title: {titles}, link: {links}")
-        self.page.goto(self.url, timeout=3000)
-        titles_list = [title.strip() for title in titles.split(',')]
-        unique_titles = list(set(titles_list))
-        unique_titles.sort()
-        titles =",".join(unique_titles)  # 去重
-        description = """We request that you take immediate actionto stop the infringing activity, take steps to ensure that iQIYI Content is notre-posted on, re-linked to, or otherwise available through your site. Pleaseinform us of the actions you have taken and their results.
-1) please help remove these videos
-2) The drama series titles are {}
-        """.format(titles)
-        # likls = ["\"" + l + "\"" for l in link]
-        # links = ','.join(likls)
-        if self.page.query_selector("div.cf-turnstile[data-sitekey]"):
-            ok = solve_turnstile_capsolver(self.page)
-            if not ok:
-                raise RuntimeError("CapSolver 处理 Turnstile 失败")
-        # file_path = f'screenshots/{str(int(time.time()))}_{title}_{link.split("/")[-1]}.png'
-        # self.page.screenshot(path=file_path)
-        resports = self.page.locator('li.blocks-item:nth-child(8)')
-        resports.click()
-
-        time.sleep(2)
-
-        cc = self.page.locator("input#request_collaborators_")
-        cc.scroll_into_view_if_needed()
-        cc.click()
-        cc.type("duke.chen@dailymotion.com")
-
-        self.page.get_by_role("button", name="Copyright infringement").click()
-        time.sleep(1)
-        self.page.get_by_role("button", name="Notification").nth(0).click()
-        time.sleep(1)
-        self.page.get_by_role("button", name="A legal entity").click()
-        time.sleep(1)
-        self.page.get_by_label("Corporate name").fill("Beijing iQIYI Science & Technology Co.,Ltd")
-        time.sleep(1)
-        self.page.get_by_label("Legal status").fill("Legal Department")
-        time.sleep(1)
-        self.page.get_by_label("Subject").fill("Copyright infringement Notification")
-        time.sleep(1)
-        self.page.get_by_label("Please indicate the URL of the video(s) you would like to report*").fill(links)
-        time.sleep(1)
-        self.page.get_by_label("Description").nth(1).fill(description)
-        time.sleep(1)
-        self.page.get_by_label("I state in good faith", exact=False).check()
-        time.sleep(1)
-        self.page.get_by_label("I state in good faith that the use of the Protected", exact=False).check()
-        time.sleep(1)
-        self.page.get_by_role("checkbox", name="I certify that all information provided", exact=False).check()
-        time.sleep(1)
-        self.page.get_by_role("checkbox", name="I acknowledge that my statements", exact=False).check()
-        time.sleep(1)
-        self.page.get_by_role("checkbox", name="The data provided through this form", exact=False).check()
-        time.sleep(1)
-        self.page.get_by_role("checkbox", name="By submitting the present form,", exact=False).check()
-        time.sleep(1)
-        self.page.get_by_role("textbox", name="electronic signature", exact=False).fill("柴达") # 占位
-        time.sleep(1)
-        self.page.set_input_files('input#request-attachments', [
-            self.file_path,
-            self.file_path2
-        ])
-        self.page.wait_for_timeout(8000)
-        self.page.get_by_role("button", name="Submit").click()
-        time.sleep(2)
-        file_path = f'screenshots/{str(int(time.time()))}_{title}_{link.split("/")[-1]}.png'
-        locator = self.page.locator("//dt[normalize-space(.)='Id']/following-sibling::dd[1]")
-        raw_text = locator.text_content()
-        match = re.search(r'\d+', raw_text or '')
-        report_id = match.group() if match else None
-        status_raw = self.page.locator("span.status-label").text_content()
-        subsequent_status = status_raw.strip().lower() if status_raw else None
-        time_elem = self.page.locator("dt", has_text="Created").locator("xpath=following-sibling::dd[1]/time")
-
-        datetime_str = time_elem.get_attribute("datetime")  # e.g. 2025-06-12T06:15:33+00:00
-        if datetime_str:
-            dt = datetime.fromisoformat(datetime_str.replace("Z", "+00:00"))  # 安全处理 ISO 时间
-            timestamp = int(dt.timestamp())
-        else:
-            timestamp = None
-        self.page.screenshot(path=file_path)
-        if self.page.url != self.url:
-            self.page.goto(self.url, timeout=30000)
-
-        return ids, file_path, report_id, subsequent_status, timestamp
-
-    @require_login
-    def report_follow_up(self, report_id: str):
-        max_retries = 3
-        retry_delay = 2
-        loaded = False
-        subsequent_status = ""
-
-        for attempt in range(max_retries):
-            try:
-                self.page.goto(f"https://faq.dailymotion.com/hc/en-us/requests/{report_id}", timeout=30000)
-                # self.page.wait_for_load_state("networkidle")  # 保证页面加载稳定
-                self.page.wait_for_selector("span.status-label", timeout=30000)
-                try:
-                    status_raw = self.page.locator("span.status-label").text_content()
-                except Exception as e:
-                    print(f"[警告] 获取状态标签失败: {e}")
-                    status_raw = None
-
-                subsequent_status = status_raw.strip().lower() if status_raw else None
-                loaded = True
-                break
-            except Exception as e:
-                print(f"[ERROR] 尝试 {attempt + 1}/{max_retries} 失败: {e}")
-                if attempt < max_retries - 1:
-                    time.sleep(retry_delay)
-
-        if not loaded:
-            return 1, "页面加载失败"
-
-        txt = (
-            "I am the authorized agent of Beijing iQIYI Technology Co., Ltd., responsible for dealing with "
-            "unauthorized overseas distribution of pirated videos of our works. "
-            "We have confirmed that the above links contain infringing content and we insist on requesting to takedown. Thank you!"
-        )
-
-        if "awaiting your reply" in subsequent_status:
-            span_show = self.page.locator('span.comment-show-container-content')
-            if span_show.count() > 0:
-                span_show.nth(0).click()
-                self.page.wait_for_timeout(1000)
-
-            textarea = self.page.locator('#request_comment_body')
-            textarea.type(txt, delay=30)
-            self.page.wait_for_timeout(1000)
-            self.page.get_by_role("button", name="Submit").click()
-
-            success = self.wait_for_selector_safe("span.status-label", timeout=30000, retries=3)
-            if not success:
-                return 1, "提交后未检测到状态更新"
-
-            span_show = self.page.locator('span.comment-show-container-content')
-            if span_show.count() > 0:
-                span_show.nth(0).click()
-            pic_path = f'screenshots/{str(int(time.time()))}_{report_id}.png'
-            self.page.screenshot(path=pic_path)
-            return 0, pic_path
-
-        elif "open" in subsequent_status:
-            return 1, ""
-
-        elif "solved" in subsequent_status:
-            return 2, ""
-
-        return 0, "未知状态"
-
-    def wait_for_selector_safe(self, selector: str, timeout=30000, retries=3, retry_delay=2):
-        for i in range(retries):
-            try:
-                self.page.wait_for_selector(selector, timeout=timeout)
-                return True
-            except Exception as e:
-                print(f"[重试] 第 {i + 1}/{retries} 次等待 {selector} 失败: {e}")
-                if i < retries - 1:
-                    time.sleep(retry_delay)
-        return False
-
-    @require_login
-    def test(self):
-        logger.info(f"Testing DailymotionClient with email: {self.email}")
-        self.page.goto(self.url, timeout=30000)
-        file_path = f'screenshots/{str(int(time.time()))}_test.png'
-        self.page.screenshot(path=file_path)
-        self.page.wait_for_timeout(1000)
-        file_path = f"screenshots/{str(int(time.time()))}_test2.png"
-        self.page.screenshot(path=file_path)
-        logger.info(f"Test screenshot saved to {file_path}")
-        self.page.wait_for_timeout(1000)
-        file_path = f"screenshots/{str(int(time.time()))}_test3.png"
-        self.page.screenshot(path=file_path)
-        logger.info(f"Test screenshot saved to {file_path}")
-
-    def close(self):
-        try:
-            self.page.close()
-        except Exception:
-            pass
-        try:
-            self.browser.close()
-        except Exception:
-            pass
-        try:
-            self._pw.stop()
-        except Exception:
-            pass
-
-
-if __name__ == "__main__":
-    dm = DailymotionClient("copyright@qiyi.com", "ppsIQIYI2018@")
-    # dm.process_ticket("恋爱学园","https://www.dailymotion.com/video/x9lfr24")
-    dm.report_follow_up("13566")

report_video_infringement.py

@@ -1,66 +1,10 @@
 import time
+
+import requests
 import json
 import redis
-import requests
-import urllib3
-from matplotlib.artist import allow_rasterization
-from requests.adapters import HTTPAdapter
-from urllib3.util.retry import Retry
-from typing import Optional, Dict, Any, Union
-
-
-class HttpClient:
-    def __init__(self, max_retries: int = 3, backoff_factor: float = 0.5):
-        self.session = requests.Session()
-        # 配置重试策略
-        retry_strategy = Retry(
-            total=max_retries,
-            backoff_factor=backoff_factor,
-            status_forcelist=[500, 502, 503, 504, 429]
-        )
-
-        adapter = HTTPAdapter(max_retries=retry_strategy)
-        self.session.mount("http://", adapter)
-        self.session.mount("https://", adapter)
-
-    def request(self,
-                method: str,
-                url: str,
-                headers: Optional[Dict] = None,
-                params: Optional[Dict] = None,
-                data: Optional[Union[Dict, str]] = None,
-                cookies: Optional[Dict] = None,
-                allow_redirects: bool = True,
-                timeout: int = 30,
-                **kwargs) -> requests.Response:
-        try:
-            response = self.session.request(
-                method=method,
-                url=url,
-                headers=headers,
-                params=params,
-                data=data,
-                cookies=cookies,
-                allow_redirects=allow_redirects,
-                timeout=timeout,
-                **kwargs
-            )
-            response.raise_for_status()
-            return response
-        except requests.exceptions.RequestException as e:
-            print(f"请求失败: {url}, 错误: {str(e)}")
-            raise
-
-    def get(self, url: str, **kwargs) -> requests.Response:
-        return self.request("GET", url, **kwargs)
-
-    def post(self, url: str, **kwargs) -> requests.Response:
-        return self.request("POST", url, **kwargs)
-
-
-# 创建全局的 HTTP 客户端实例
-http_client = HttpClient()
 
+session = requests.Session()
 _REDIS_CONF = {
     "host": "192.144.230.75",
     "port": 6379,
@@ -88,197 +32,151 @@ def get_report_token(key_name: str):
 
 
 def login():
-    try:
-        headers = {
-            "Accept": "*/*",
-            "Accept-Language": "zh-CN,zh;q=0.9",
-            "Cache-Control": "no-cache",
-            "Connection": "keep-alive",
-            "Content-Type": "application/x-www-form-urlencoded",
-            "Origin": "https://www.dailymotion.com",
-            "Pragma": "no-cache",
-            "Referer": "https://www.dailymotion.com/",
-            "Sec-Fetch-Dest": "empty",
-            "Sec-Fetch-Mode": "cors",
-            "Sec-Fetch-Site": "same-site",
-            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/136.0.0.0 Safari/537.36 Edg/136.0.0.0",
-            "sec-ch-ua": "\"Chromium\";v=\"136\", \"Microsoft Edge\";v=\"136\", \"Not.A/Brand\";v=\"99\"",
-            "sec-ch-ua-mobile": "?0",
-            "sec-ch-ua-platform": "\"Windows\""
-        }
-        url = "https://graphql.api.dailymotion.com/oauth/token"
-        data = {
-            "client_id": "f1a362d288c1b98099c7",
-            "client_secret": "eea605b96e01c796ff369935357eca920c5da4c5",
-            "grant_type": "password",
-            "username": "copyright@qiyi.com",
-            "password": "ppsIQIYI2018@",
-            "scope": "userinfo,email,manage_subscriptions,manage_history,manage_likes,manage_playlists,manage_videos",
-            "version": "2",
-            "traffic_segment": "962042",
-            "visitor_id": "359703fb-66c2-43d2-bd0d-b1cac9c7ae8a"
-        }
-        response = http_client.post(url, headers=headers, data=data)
-        data = {
-            "update_time": int(time.time()),
-            "username": "copyright@qiyi.com",
-            "password": "ppsIQIYI2018@",
-            "token": response.json()
-        }
-        save_report_token('token', data)
-        return data
-    except Exception as e:
-        print(f"登录失败: {str(e)}")
-        raise
-
-
-def refresh_token(access_token, refresh_token):
     headers = {
         "Accept": "*/*",
         "Accept-Language": "zh-CN,zh;q=0.9",
         "Cache-Control": "no-cache",
         "Connection": "keep-alive",
-        "Content-Length": "0",
+        "Content-Type": "application/x-www-form-urlencoded",
         "Origin": "https://www.dailymotion.com",
         "Pragma": "no-cache",
-        "Referer": "https://www.dailymotion.com/signin?urlback=%2Fzendesk%3Ftimestamp%3D1748932650%26return_to%3Dhttps%253A%252F%252Ffaq.dailymotion.com%252Fhc%252Fen-us%252Frequests%252Fnew",
+        "Referer": "https://www.dailymotion.com/",
         "Sec-Fetch-Dest": "empty",
         "Sec-Fetch-Mode": "cors",
-        "Sec-Fetch-Site": "same-origin",
+        "Sec-Fetch-Site": "same-site",
         "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/136.0.0.0 Safari/537.36 Edg/136.0.0.0",
         "sec-ch-ua": "\"Chromium\";v=\"136\", \"Microsoft Edge\";v=\"136\", \"Not.A/Brand\";v=\"99\"",
         "sec-ch-ua-mobile": "?0",
         "sec-ch-ua-platform": "\"Windows\""
     }
+    url = "https://graphql.api.dailymotion.com/oauth/token"
+    data = {
+        "client_id": "f1a362d288c1b98099c7",
+        "client_secret": "eea605b96e01c796ff369935357eca920c5da4c5",
+        "grant_type": "password",
+        "username": "copyright@qiyi.com",
+        "password": "ppsIQIYI2018@",
+        "scope": "userinfo,email,manage_subscriptions,manage_history,manage_likes,manage_playlists,manage_videos",
+        "version": "2",
+        "traffic_segment": "962042",
+        "visitor_id": "359703fb-66c2-43d2-bd0d-b1cac9c7ae8a"
+    }
+    response = session.post(url, headers=headers, data=data)
+    data = {
+        "update_time": int(time.time()),
+        "username": "copyright@qiyi.com",
+        "password": "ppsIQIYI2018@",
+        "token": response.json()
+    }
+    save_report_token('token', data)
+    return data
+
+
+def get_cookies(access_token: str, refresh_token: str):
     cookies = {
-        "dmvk": "683e982c34e34",
-        "ts": "133696",
-        "v1st": "a847389a-6b91-4157-948f-457666f7172b",
-        "ff": "on",
-        "lang": "zh_CN",
-        "usprivacy": "1---",
-        "dmaid": "73ca37e4-6858-46c1-aac4-a4a5fc9a270e",
-        "cookie_policy_closed": "1",
         "access_token": access_token,
         "refresh_token": refresh_token,
     }
     url = "https://www.dailymotion.com/cookie/refresh_token"
-    response = http_client.post(url, headers=headers, cookies=cookies)
+    session.post(url, cookies=cookies, allow_redirects=True)
 
 
-def zendesk():
-    headers = {
-        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
-        "Accept-Language": "zh-CN,zh;q=0.9",
-        "Cache-Control": "no-cache",
-        "Connection": "keep-alive",
-        "Pragma": "no-cache",
-        "Referer": "https://www.dailymotion.com/sg",
-        "Sec-Fetch-Dest": "document",
-        "Sec-Fetch-Mode": "navigate",
-        "Sec-Fetch-Site": "same-origin",
-        "Sec-Fetch-User": "?1",
-        "Upgrade-Insecure-Requests": "1",
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/136.0.0.0 Safari/537.36 Edg/136.0.0.0",
-        "sec-ch-ua": "\"Chromium\";v=\"136\", \"Microsoft Edge\";v=\"136\", \"Not.A/Brand\";v=\"99\"",
-        "sec-ch-ua-mobile": "?0",
-        "sec-ch-ua-platform": "\"Windows\""
+def get_cookies1(access_token: str, refresh_token: str):
+    """302 跳转"""
+    cookies = {
+        "access_token": access_token,
+        "refresh_token": refresh_token,
     }
     url = "https://www.dailymotion.com/zendesk"
     params = {
         "return_to": "https://faq.dailymotion.com/hc/en-us/requests/new",
-        "timestamp": str(time.time()),
+        "timestamp": str(int(time.time())),
     }
-    response = http_client.get(url, headers=headers, params=params, allow_redirects=True)
-    data = http_client.session.cookies.get_dict()
-    data['update_time'] = int(time.time())
-    save_report_token('cookies', data)
+    session.get(url, cookies=cookies, params=params, allow_redirects=True)
+    cookies_dict = {"update_time": int(time.time()), "cookies": session.cookies.get_dict()}
+    save_report_token('cookies', cookies_dict)
+    return cookies_dict
 
 
 def get_csrftoken():
-    try:
-        url = "https://faq.dailymotion.com/hc/api/internal/csrf_token.json"
-        headers = {
-            "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
-            "Accept-Language": "zh-CN,zh;q=0.9",
-            "Cache-Control": "no-cache",
-            "Connection": "keep-alive",
-            "Pragma": "no-cache",
-            "Referer": "https://www.dailymotion.com/sg",
-            "Sec-Fetch-Dest": "document",
-            "Sec-Fetch-Mode": "navigate",
-            "Sec-Fetch-Site": "same-origin",
-            "Sec-Fetch-User": "?1",
-            "Upgrade-Insecure-Requests": "1",
-            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/136.0.0.0 Safari/537.36 Edg/136.0.0.0",
-            "sec-ch-ua": "\"Chromium\";v=\"136\", \"Microsoft Edge\";v=\"136\", \"Not.A/Brand\";v=\"99\"",
-            "sec-ch-ua-mobile": "?0",
-            "sec-ch-ua-platform": "\"Windows\""
-        }
-        response = http_client.get(url, headers=headers)
-        data = {"update_time": int(time.time()), "csrf_token": response.json()}
-        save_report_token('csrf_token', data)
-        return data
-    except Exception as e:
-        print(f"获取 CSRF token 失败: {str(e)}")
-        raise
+    url = "https://faq.dailymotion.com/hc/api/internal/csrf_token.json"
+    response = session.get(url)
+    data = {"update_time": int(time.time()), "csrf_token": response.json()}
+    save_report_token('csrf_token', data)
+    return data
 
 
-def report(csrf_token: str, v_url, title):
-    try:
-        headers = {
-            "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
-            "accept-language": "zh-CN,zh;q=0.9",
-            "cache-control": "no-cache",
-            "content-type": "application/x-www-form-urlencoded",
-            "origin": "https://faq.dailymotion.com",
-            "pragma": "no-cache",
-            "priority": "u=0, i",
-            "referer": "https://faq.dailymotion.com/hc/en-us/requests/new?ticket_form_id=136048",
-            "sec-ch-ua": "\"Chromium\";v=\"136\", \"Microsoft Edge\";v=\"136\", \"Not.A/Brand\";v=\"99\"",
-            "sec-ch-ua-mobile": "?0",
-            "sec-ch-ua-platform": "\"Windows\"",
-            "sec-fetch-dest": "document",
-            "sec-fetch-mode": "navigate",
-            "sec-fetch-site": "same-origin",
-            "sec-fetch-user": "?1",
-            "upgrade-insecure-requests": "1",
-            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/136.0.0.0 Safari/537.36 Edg/136.0.0.0"
-        }
-        url = "https://faq.dailymotion.com/hc/en-us/requests"
-        data = {
-            "utf8": "✓",
-            "authenticity_token": csrf_token,
-            "request%5Bticket_form_id%5D": "136048",
-            "request%5Bcollaborators%5D%5B%5D": "duke.chen@dailymotion.com",
-            "request%5Bcustom_fields%5D%5B360008684839%5D": "__dc.copyright_user_protection_-_copyright__",
-            "request%5Bcustom_fields%5D%5B30150188%5D": "copyrightform-notification",
-            "request%5Bcustom_fields%5D%5B25089567%5D": "legal_entity",
-            "request%5Bcustom_fields%5D%5B25159868%5D": "Beijing iQIYI Science & Technology Co.,Ltd",
-            "request%5Bcustom_fields%5D%5B4869133282962%5D": "Legal Department",
-            "request%5Bsubject%5D": "Copyright infringement Notification",
-            "request%5Bcustom_fields%5D%5B25613698%5D": v_url,
-            "request%5Bdescription%5D": f"We request that you take immediate actionto stop the infringing activity, take steps to ensure that iQIYI Content is notre-posted on, re-linked to, or otherwise available through your site. Pleaseinform us of the actions you have taken and their results.\r\n1) please help remove these videos\r\n2) The drama series titles are \"{title}\"\r\n",
-            "request%5Bdescription_mimetype%5D": "text/plain",
-            "request%5Bcustom_fields%5D%5B4769880845586%5D": "on",
-            "request%5Bcustom_fields%5D%5B25626417%5D": "on",
-            "request%5Bcustom_fields%5D%5B4769797363346%5D": "on",
-            "request%5Bcustom_fields%5D%5B25159848%5D": "on",
-            "request%5Bcustom_fields%5D%5B4769658191250%5D": "on"
-        }
-        response = requests.post(url, headers=headers, data=data)
-        print(response.status_code)
-        print(response.text)
-        print(response)
-        return response.status_code == 200
-    except Exception as e:
-        print(f"提交报告失败: {str(e)}")
-        raise
+def report(csrf_token:str, cookies:dict, ):
+    headers = {
+        'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
+        'accept-language': 'zh-CN,zh;q=0.9',
+        'cache-control': 'no-cache',
+        'content-type': 'application/x-www-form-urlencoded',
+        'origin': 'https://faq.dailymotion.com',
+        'pragma': 'no-cache',
+        'priority': 'u=0, i',
+        'referer': 'https://faq.dailymotion.com/hc/en-us/requests/new?ticket_form_id=136048',
+        'sec-ch-ua': '"Chromium";v="136", "Google Chrome";v="136", "Not.A/Brand";v="99"',
+        'sec-ch-ua-mobile': '?0',
+        'sec-ch-ua-platform': '"Windows"',
+        'sec-fetch-dest': 'document',
+        'sec-fetch-mode': 'navigate',
+        'sec-fetch-site': 'same-origin',
+        'sec-fetch-user': '?1',
+        'upgrade-insecure-requests': '1',
+        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/136.0.0.0 Safari/537.36',
+    }
+
+    data = {
+        'utf8': '✓',
+        'authenticity_token': csrf_token,
+        'request[ticket_form_id]': '136048',
+        'request[collaborators][]': 'duke.chen@dailymotion.com',
+        'request[custom_fields][360008684839]': '__dc.copyright_user_protection_-_copyright__',
+        'request[custom_fields][30150188]': 'copyrightform-notification',
+        'request[custom_fields][25089567]': 'legal_entity',
+        'request[custom_fields][25159868]': 'Beijing iQIYI Science & Technology Co.,Ltd',
+        'request[custom_fields][4869133282962]': 'Legal Department',
+        'request[subject]': 'Copyright infringement Notification',
+        'request[custom_fields][25613698]': 'url',
+        'request[description]': 'We request that you take immediate actionto stop the infringing activity, take steps to ensure that iQIYI Content is notre-posted on, re-linked to, or otherwise available through your site. Pleaseinform us of the actions you have taken and their results.\r\n1) please help remove these videos\r\n2) The drama series titles are 片名\r\n',
+        'request[description_mimetype]': 'text/plain',
+        'request[custom_fields][4769880845586]': [
+            'off',
+            'on',
+        ],
+        'request[custom_fields][25626417]': [
+            'off',
+            'on',
+        ],
+        'request[custom_fields][4769797363346]': [
+            'off',
+            'on',
+        ],
+        'request[custom_fields][25159848]': [
+            'off',
+            'on',
+        ],
+        'request[custom_fields][4769658191250]': [
+            'off',
+            'on',
+        ],
+    }
+
+    response = requests.post('https://faq.dailymotion.com/hc/en-us/requests', cookies=cookies, headers=headers, data=data)
 
 
+def prepare_data():
+    token = get_report_token('token')
+    cookies = get_report_token('cookies')
+    csrf_token = get_report_token('csrf_token')
+    max_update_time = max(d.get('update_time', 0) for d in (token, cookies, csrf_token) if d)
+    if max_update_time + (24 * 60 * 60) < time.time():
+        token = get_report_token('token')
+        access_token = token['token']['access_token']
+        refresh_token = token['token']['refresh_token']
+        get_cookies(access_token, refresh_token)
+        get_cookies1(access_token, refresh_token)
+        csrf_token = get_csrftoken()
 
-if __name__ == '__main__':
-    cookies = get_report_token('cookies')['cookies']
-    http_client.session.cookies = requests.utils.cookiejar_from_dict(cookies)
-    csrf_token = get_csrftoken()['csrf_token']['current_session']['csrf_token']
-    report(csrf_token, 'Hunter X Hunter', 'https://www.dailymotion.com/video/x8kjx7v')
+    report(csrf_token['csrf_token']['current_session']['csrf_token'], cookies['cookies'])

requirements.txt

@@ -4,7 +4,8 @@ charset-normalizer==3.4.2
 et-xmlfile==1.1.0
 idna==3.10
 importlib-metadata==6.7.0
-numpy==2.3.0
+lxml==5.4.0
+numpy==1.21.6
 openpyxl==3.1.3
 pandas==1.3.5
 pkg_resources==0.0.0

screenshots_flask.py

@@ -1,35 +0,0 @@
-from flask import Flask, send_file, abort, request, jsonify
-from pathlib import Path
-
-app = Flask(__name__)
-
-PROJECT_ROOT = Path(__file__).parent.resolve()
-SCREENSHOTS_DIR = Path("/opt/ql/daily_com/bin/screenshots").resolve()
-
-@app.route('/image/screenshots/<path:filename>')
-def serve_image(filename):
-    file_path = SCREENSHOTS_DIR / filename
-
-    # 防止路径越界访问
-    try:
-        file_path.resolve().relative_to(SCREENSHOTS_DIR.resolve())
-    except ValueError:
-        abort(403, description=f"禁止访问目录外文件: {file_path.resolve()}")
-
-    if not file_path.exists():
-        abort(404, description=f"文件不存在: {file_path.resolve()}")
-
-    return send_file(file_path, as_attachment=False)
-
-# 自定义 404 错误响应
-@app.errorhandler(404)
-def handle_404(e):
-    return f"404 错误：{e.description}", 404
-
-# 自定义 403 错误响应
-@app.errorhandler(403)
-def handle_403(e):
-    return f"403 错误：{e.description}", 403
-
-if __name__ == '__main__':
-    app.run(host='0.0.0.0', debug=False, port=5000)

test2.py

@@ -1,6 +0,0 @@
-from DB import DBVidcon
-
-db = DBVidcon()
-
-account = db.get_account_info('4')
-print(account)

update_video_tsstatus.py

@@ -1,10 +0,0 @@
-from DB import DBVidcon
-from logger import logger
-
-
-db = DBVidcon()
-
-logger.info("开始更新视频举报状态")
-db.update_video_ts_status()
-db.close()
-logger.info("更改视频举报状态完成")