626 lines
18 KiB
Python
626 lines
18 KiB
Python
import base64
|
|
from datetime import datetime
|
|
|
|
import requests
|
|
import uuid
|
|
import random
|
|
import time
|
|
import copy
|
|
from threading import Lock
|
|
import logging
|
|
from DB import DBVidcon
|
|
import json
|
|
from requests.adapters import HTTPAdapter
|
|
from urllib3.util.retry import Retry
|
|
|
|
MACHINE_ID = 3
|
|
logger = logging.getLogger(__name__)
|
|
db = DBVidcon()
|
|
proxiesdict = db.get_proxy_agent_dict()
|
|
|
|
def clean_dash_to_zero(val):
|
|
if val in ('-', '', None):
|
|
return 0
|
|
try:
|
|
return int(val)
|
|
except (ValueError, TypeError) as e:
|
|
logger.exception(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:
|
|
logger.exception(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:
|
|
for attempt in range(retry + 1):
|
|
try:
|
|
return self._generate_headers()
|
|
except Exception as e:
|
|
logger.warning(f"[get_headers] 第 {attempt + 1} 次尝试失败: {e}")
|
|
time.sleep(2)
|
|
|
|
with self._cache_lock:
|
|
if self._headers_cache:
|
|
logger.info("[get_headers]")
|
|
return copy.deepcopy(self._headers_cache)
|
|
|
|
logger.warning("[get_headers] 基础 headers")
|
|
return copy.deepcopy(self._headers_template)
|
|
|
|
def _generate_headers(self) -> 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 = requests.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
|
|
self.session = self._create_session()
|
|
|
|
def _create_session(self):
|
|
session = requests.Session()
|
|
retry = Retry(
|
|
total=self.max_retries,
|
|
connect=self.max_retries,
|
|
read=self.max_retries,
|
|
backoff_factor=self.backoff_factor,
|
|
status_forcelist=[500, 502, 503, 504],
|
|
allowed_methods=["GET"]
|
|
)
|
|
adapter = HTTPAdapter(max_retries=retry)
|
|
session.mount("http://", adapter)
|
|
session.mount("https://", adapter)
|
|
|
|
if self.proxies:
|
|
session.proxies.update(self.proxies)
|
|
|
|
return session
|
|
|
|
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 = self.session.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')
|
|
data["v_id"] = vid
|
|
data["v_title"] = r_data["title"]
|
|
data["link"] = "https://www.dailymotion.com/video/" + xid,
|
|
data["duration"] = r_data["duration"]
|
|
data['createdtime'] = datetime.fromtimestamp(r_data.get("created_time")).strftime("%Y-%m-%d %H:%M:%S"),
|
|
data['']
|
|
except requests.RequestException as e:
|
|
print(f"[ERROR] 请求失败 vxid={v_xid} : {e}")
|
|
return None
|
|
|
|
|
|
|
|
def main():
|
|
kwdata = db.get_web_items()
|
|
if not kwdata:
|
|
logger.error("没有获取到关键词数据")
|
|
exit(1)
|
|
|
|
kwdata = kwdata[0][1]
|
|
rn = kwdata['rn']
|
|
proxy_name = proxiesdict.get(rn)
|
|
proxies_str = db.get_proxy(proxy_name, '-1')
|
|
proxies = {
|
|
'http': proxies_str,
|
|
'https': proxies_str
|
|
}
|
|
kw = kwdata['keyword']
|
|
|
|
dmheader_manager = DMHeaderManager(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 = requests.post('https://graphql.api.dailymotion.com/', headers=headers, data=payload,
|
|
proxies=proxies)
|
|
|
|
data = response.json()
|
|
edges = data['data']['search']['stories']['edges']
|
|
edges_len = len(edges)
|
|
dm_video_info = DMVideoInfo(proxies=proxies)
|
|
tancks = []
|
|
for j, edge in enumerate(edges):
|
|
node = edge.get("node", {})
|
|
tancks.append({
|
|
"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,
|
|
})
|
|
|
|
if edges_len < 20:
|
|
break
|