import json import random import time import uuid import pandas as pd import requests import os from requests import RequestException BASE_DIR = os.path.dirname(os.path.abspath(__file__)) kw_path = os.path.join(BASE_DIR, 'data', 'keyword1.xlsx') headers1 = { 'Accept': '*/*, */*', # 'Accept-Encoding': 'gzip, deflate, br', 'Cache-Control': 'no-cache', 'Connection': 'keep-alive', # 'Content-Length': '6237', '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 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/135.0.0.0 Safari/537.36', 'X-DM-AppInfo-Id': 'com.dailymotion.neon', 'X-DM-AppInfo-Type': 'website', 'X-DM-AppInfo-Version': 'v2025-04-28T12:37:52.391Z', 'X-DM-Neon-SSR': '0', 'X-DM-Preferred-Country': 'us', 'accept-language': 'zh-CN', 'authorization': 'Bearer eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.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.bMzShOLIb6datC92qGPTRVCW9eINTYDFwLtqed2P1d4', 'sec-ch-ua': '"Google Chrome";v="135", "Not-A.Brand";v="8", "Chromium";v="135"', 'sec-ch-ua-mobile': '?0', 'sec-ch-ua-platform': '"Windows"', 'x-dm-visit-id': '1745971699160', 'x-dm-visitor-id': '64633D03065F4186AD0B027CF795EF0F', } # proxies = None proxies = { "http": 'http://127.0.0.1:7890', "https": 'http://127.0.0.1:7890', } def post_with_retry(url, json_payload=None, data=None, headers=None, proxies=None, retries=3, timeout=10, backoff_factor=1): """ 向指定 URL 发起 POST 请求，遇到网络错误时最多重试 `retries` 次。 :param url: 请求地址 :param json_payload: 要发送的 JSON 体 :param headers: 可选的请求头 dict :param proxies: 可选的代理 dict :param retries: 重试次数 :param timeout: 单次请求超时(秒) :param backoff_factor: 重试间隔基数（会指数级增长） :return: requests.Response 对象 :raises: 最后一次仍失败时抛出最后的异常 """ attempt = 0 while attempt < retries: try: if json_payload is not None: response = requests.post( url, json=json_payload, headers=headers, proxies=proxies, timeout=timeout ) else: response = requests.post( url, data=data, headers=headers, proxies=proxies, timeout=timeout ) response.raise_for_status() return response except RequestException as e: time.sleep(100) attempt += 1 print(f"[{attempt}/{retries}] 请求失败: {e}") if attempt == retries: print("已达最大重试次数，抛出异常。") raise sleep_time = backoff_factor * (2 ** (attempt - 1)) print(f"等待 {sleep_time} 秒后重试…") time.sleep(sleep_time) def red_keyword_info(): df = pd.read_excel(kw_path, sheet_name=0) records = df.to_dict(orient='records') print(f"共 {len(records)} 行数据：") return records def gettoken(): 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/135.0.0.0 Safari/537.36', 'sec-ch-ua': '"Google Chrome";v="135", "Not-A.Brand";v="8", "Chromium";v="135"', 'sec-ch-ua-mobile': '?0', 'sec-ch-ua-platform': '"Windows"', } u = uuid.uuid4() uuid_with_dash = str(u) uuid_no_dash = u.hex data = { 'client_id': 'f1a362d288c1b98099c7', 'client_secret': 'eea605b96e01c796ff369935357eca920c5da4c5', 'grant_type': 'client_credentials', 'traffic_segment': '567786', 'visitor_id': uuid_with_dash, } url = 'https://graphql.api.dailymotion.com/oauth/token' response = post_with_retry(url, headers=headers, data=data, proxies=proxies) token = response.json()['access_token'] headers1['authorization'] = "Bearer " + token headers1['x-dm-visit-id'] = str(int(time.time() * 1000)) headers1['x-dm-visitor-id'] = uuid_no_dash def get_searchInfo(keyword): video_list = [] user_list = [] for j in range(1, 3): # 别展开 = = ! data = { "operationName": "SEARCH_QUERY", "variables": { "query": keyword, "shouldIncludeTopResults": True, "shouldIncludeChannels": False, "shouldIncludePlaylists": False, "shouldIncludeHashtags": False, "shouldIncludeVideos": False, "shouldIncludeLives": False, "page": j, "limit": 100, "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 } } """ } gettoken() response = post_with_retry( "https://graphql.api.dailymotion.com/", json_payload=data, headers=headers1, proxies=proxies ) jsondata = response.json() try: resinfo = jsondata['data']['search']['stories']['edges'] print('resinfo :', len(resinfo)) except Exception: resinfo = [] ValueError("返回字段解析错误!") for index, iteminfo in enumerate(resinfo): calculated_index = index + 1 + (j - 1) * 100 print(calculated_index) node = iteminfo['node'] __typename = node['__typename'] if __typename == "Video": xid = node.get('xid') v_info = get_videoInfo(xid) time.sleep(3) video_list.append({ "index": calculated_index, "id": node.get('id'), "xid": xid, "link": "https://www.dailymotion.com/video/" + xid, "title": node.get('title'), "createtime": node.get('createdAt'), "duration": node.get('duration'), "pic": node.get('thumbnail').get('url'), "view": v_info['view'], "fans": v_info['fans'], "videos": v_info['videos'] }) elif __typename == "Channel": user_list.append({ 'index': calculated_index, 'id': node['id'], 'xid': node['xid'], 'name': node['name'], 'upic': node['avatar']['url'] }) else: continue time.sleep(15) return video_list, user_list def get_videoInfo(x_id, r=3): payload = { "operationName": "WATCHING_VIDEO", "variables": { "xid": x_id, "isSEO": False }, "query": "fragment VIDEO_FRAGMENT on Video {\n id\n xid\n isPublished\n duration\n title\n description\n thumbnailx60: thumbnailURL(size: \"x60\")\n thumbnailx120: thumbnailURL(size: \"x120\")\n thumbnailx240: thumbnailURL(size: \"x240\")\n thumbnailx360: thumbnailURL(size: \"x360\")\n thumbnailx480: thumbnailURL(size: \"x480\")\n thumbnailx720: thumbnailURL(size: \"x720\")\n thumbnailx1080: thumbnailURL(size: \"x1080\")\n aspectRatio\n category\n categories(filter: {category: {eq: CONTENT_CATEGORY}}) {\n edges {\n node { id name slug __typename }\n __typename\n }\n __typename\n }\n iab_categories: categories(\n filter: {category: {eq: IAB_CATEGORY}, percentage: {gte: 70}}\n ) {\n edges {\n node { id slug __typename }\n __typename\n }\n __typename\n }\n bestAvailableQuality\n createdAt\n viewerEngagement {\n id\n liked\n favorited\n __typename\n }\n isPrivate\n isWatched\n isCreatedForKids\n isExplicit\n canDisplayAds\n videoWidth: width\n videoHeight: height\n status\n hashtags {\n edges {\n node { id name __typename }\n __typename\n }\n __typename\n }\n stats {\n id\n views { id total __typename }\n __typename\n }\n channel {\n __typename\n id\n xid\n name\n displayName\n isArtist\n logoURLx25: logoURL(size: \"x25\")\n logoURL(size: \"x60\")\n isFollowed\n accountType\n coverURLx375: coverURL(size: \"x375\")\n stats {\n id\n views { id total __typename }\n followers { id total __typename }\n videos { id total __typename }\n __typename\n }\n country { id codeAlpha2 __typename }\n organization @skip(if: $isSEO) {\n id\n xid\n owner { id xid __typename }\n __typename\n }\n }\n language { id codeAlpha2 __typename }\n tags {\n edges {\n node { id label __typename }\n __typename\n }\n __typename\n }\n moderation { id reviewedAt __typename }\n topics(whitelistedOnly: true, first: 3, page: 1) {\n edges {\n node {\n id\n xid\n name\n names {\n edges {\n node {\n id\n name\n language { id codeAlpha2 __typename }\n __typename\n }\n __typename\n }\n __typename\n }\n __typename\n }\n __typename\n }\n __typename\n }\n geoblockedCountries {\n id\n allowed\n denied\n __typename\n }\n transcript {\n edges {\n node { id timecode text __typename }\n __typename\n }\n __typename\n }\n __typename\n}\n\nfragment LIVE_FRAGMENT on Live {\n id\n xid\n startAt\n endAt\n isPublished\n title\n description\n thumbnailx60: thumbnailURL(size: \"x60\")\n thumbnailx120: thumbnailURL(size: \"x120\")\n thumbnailx240: thumbnailURL(size: \"x240\")\n thumbnailx360: thumbnailURL(size: \"x360\")\n thumbnailx480: thumbnailURL(size: \"x480\")\n thumbnailx720: thumbnailURL(size: \"x720\")\n thumbnailx1080: thumbnailURL(size: \"x1080\")\n aspectRatio\n category\n createdAt\n viewerEngagement { id liked favorited __typename }\n isPrivate\n isExplicit\n isCreatedForKids\n bestAvailableQuality\n canDisplayAds\n videoWidth: width\n videoHeight: height\n stats { id views { id total __typename } __typename }\n channel {\n __typename\n id\n xid\n name\n displayName\n isArtist\n logoURLx25: logoURL(size: \"x25\")\n logoURL(size: \"x60\")\n isFollowed\n accountType\n coverURLx375: coverURL(size: \"x375\")\n stats { id views { id total __typename } followers { id total __typename } videos { id total __typename } __typename }\n country { id codeAlpha2 __typename }\n organization @skip(if: $isSEO) { id xid owner { id xid __typename } __typename }\n }\n language { id codeAlpha2 __typename }\n tags { edges { node { id label __typename } __typename } __typename }\n moderation { id reviewedAt __typename }\n topics(whitelistedOnly: true, first: 3, page: 1) {\n edges { node { id xid name names { edges { node { id name language { id codeAlpha2 __typename } __typename } __typename } __typename } __typename } __typename }\n __typename\n }\n geoblockedCountries { id allowed denied __typename }\n __typename\n}\n\nquery WATCHING_VIDEO($xid: String!, $isSEO: Boolean!) {\n video: media(xid: $xid) {\n __typename\n ... on Video { id ...VIDEO_FRAGMENT __typename }\n ... on Live { id ...LIVE_FRAGMENT __typename }\n }\n}" } url = 'https://graphql.api.dailymotion.com/' response = post_with_retry( url, json_payload=payload, headers=headers1, proxies=proxies, ) jsondata = response.json() try: v_info = jsondata['data']['video']['channel']['stats'] except Exception: if r > 0: return get_videoInfo(x_id=x_id, r=r - 1) else: return { "view": '-', "fans": '-', "videos": '-', } return { "view": v_info['views']['total'], "fans": v_info['followers']['total'], "videos": v_info['videos']['total'], } def integrate_data(): keyword_list = red_keyword_info() for key_word_item in keyword_list: gettoken() Video_PD_DATA = { "片名": [], "搜索词": [], "ID": [], "xid": [], "连接地址": [], "标题": [], "时长 (秒)": [], "关注数": [], "视频数": [], "浏览数": [], "添加时间": [], "封面图片": [], "Index": [], } User_PD_DATA = { "片名": [], "搜索词": [], "ID": [], "xid": [], "名称": [], "头像": [], "Index": [], } film_name = key_word_item['片名'] key_word = key_word_item['搜索词'] print(key_word) v_list, u_list = get_searchInfo(key_word) if len(v_list) < 1 and len(u_list) < 1: i = 0 while i < 3: time.sleep(i * 5) v_list, u_list = get_searchInfo(key_word) if len(v_list) > 1 or len(u_list) > 1: print(len(v_list), len(u_list)) break i += 1 time.sleep(2) for item in v_list: Video_PD_DATA['片名'].append(film_name) Video_PD_DATA['搜索词'].append(key_word) Video_PD_DATA['ID'].append(item.get('id')) Video_PD_DATA['xid'].append(item.get('xid')) Video_PD_DATA['连接地址'].append(item.get('link')) Video_PD_DATA['标题'].append(item.get('title')) Video_PD_DATA['时长 (秒)'].append(item.get('duration')) Video_PD_DATA['关注数'].append(item.get('fans')) Video_PD_DATA['视频数'].append(item.get('videos')) Video_PD_DATA['浏览数'].append(item.get('view')) Video_PD_DATA['添加时间'].append(item.get('createtime')) Video_PD_DATA['封面图片'].append(item.get('pic')) Video_PD_DATA['Index'].append(item.get('index')) for item in u_list: User_PD_DATA['片名'].append(film_name) User_PD_DATA['搜索词'].append(key_word) User_PD_DATA['ID'].append(item.get('id')) User_PD_DATA['xid'].append(item.get('xid')) User_PD_DATA['名称'].append(item.get('name')) User_PD_DATA['头像'].append(item.get('upic')) User_PD_DATA['Index'].append(item.get('index')) df_vido = pd.DataFrame(Video_PD_DATA) df_user = pd.DataFrame(User_PD_DATA) output_path = "out_put_CNTW/{}_{}.xlsx".format(film_name, key_word) with pd.ExcelWriter(output_path, engine="openpyxl") as w: df_vido.to_excel(w, sheet_name="视频信息", index=False) df_user.to_excel(w, sheet_name="用户信息", index=False) if __name__ == '__main__': # gettoken() integrate_data() # print(get_searchInfo('Running Man'))