Python采集某手视频,1080P高清无水印,完整数据来源分析+完整代码
知识点
- 动态数据抓包
- 动态页面分析
- requests携带参数发送请求
- json数据解析
- python 3.8 更加新 稳定 运行代码
- pycharm 2021.2 辅助敲代码
- requests 第三方模块
对于本篇文章有疑问的同学可以加【资料白嫖、解答交流群:910981974】
-
右键点击检查 或者 F12 打开
-
选择network 然后刷新网页
-
随便点击打开一个视频
-
点击搜到的内容
-
依次展开查看, 去找到我们需要的视频地址
-
请求头参数
-
请求参数
- 请求方式: POST
- 请求头(伪装):
headers = { 'content-type': 'application/json', 'Cookie': '你自己的cookie', 'Host': 'www.kuaishou.com', 'Origin': 'https://www.kuaishou.com', 'Referer': 'https://www.kuaishou.com/profile/3xv78fxycm35nn4', 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36' }
- 请求参数:
data = { 'operationName': "visionProfilePhotoList", 'query': "query visionProfilePhotoList($pcursor: String, $userId: String, $page: String, $webPageArea: String) {\n visionProfilePhotoList(pcursor: $pcursor, userId: $userId, page: $page, webPageArea: $webPageArea) {\n result\n llsid\n webPageArea\n feeds {\n type\n author {\n id\n name\n following\n headerUrl\n headerUrls {\n cdn\n url\n __typename\n }\n __typename\n }\n tags {\n type\n name\n __typename\n }\n photo {\n id\n duration\n caption\n likeCount\n realLikeCount\n coverUrl\n coverUrls {\n cdn\n url\n __typename\n }\n photoUrls {\n cdn\n url\n __typename\n }\n photoUrl\n liked\n timestamp\n expTag\n animatedCoverUrl\n stereoType\n videoRatio\n profileUserTopPhoto\n __typename\n }\n canAddComment\n currentPcursor\n llsid\n status\n __typename\n }\n hostName\n pcursor\n __typename\n }\n}\n", 'variables': {'userId': "3x9dquvtb9n9fps", 'pcursor': "", 'page': "profile"} }
- 后续如果需要翻页爬取, 需要使用递归实现
url = 'https://www.kuaishou.com/graphql' # 伪装 headers = { # 控制data类型 json类型字符串 'content-type': 'application/json', 'Cookie': 'kpf=PC_WEB; kpn=KUAISHOU_VISION; clientid=3; did=web_ea128125517a46bd491ae9ccb255e242; client_key=65890b29; userId=270932146; kuaishou.server.web_st=ChZrdWFpc2hvdS5zZXJ2ZXIud2ViLnN0EqABnjkpJPZ-QanEQnI0XWMVZxXtIqPj-hwjsXBn9DHaTzispQcLjGR-5Xr-rY4VFaIC-egxv508oQoRYdgafhxSBpZYqLnApsaeuAaoLj2xMbRoytYGCrTLF6vVWJvzz3nzBVzNSyrXyhz-RTlRJP4xe1VjSp7XLNLRnVFVEtGPuBz0xkOnemy7-1-k6FEwoPIbOau9qgO5mukNg0qQ2NLz_xoSKS0sDuL1vMmNDXbwL4KX-qDmIiCWJ_fVUQoL5jjg3553H5iUdvpNxx97u6I6MkKEzwOaSigFMAE; kuaishou.server.web_ph=b282f9af819333f3d13e9c45765ed62560a1', 'Host': 'www.kuaishou.com', 'Origin': 'https://www.kuaishou.com', 'Referer': 'https://www.kuaishou.com/profile/3xauthkq46ftgkg', 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.71 Safari/537.36', } # <Response [200]>: 发送请求成功结果 response = requests.post(url=url, headers=headers, json=data)
json_data = response.json()
feeds = json_data['data']['visionProfilePhotoList']['feeds'] # 下一页需要的参数 pcursor = json_data['data']['visionProfilePhotoList']['pcursor'] # print(pcursor) for feed in feeds: caption = feed['photo']['caption'] # 标题 photoUrl = feed['photo']['photoUrl'] # 视频链接 # \: 转义字符, 直接写\ 匹配不到 \ # \\ 才能匹配到 \ # 用css和xpath 是必须要你拿到的数据是一个网页源代码 caption = re.sub('[\\/:*?"<>|\n\t]', '', caption) print(caption, photoUrl)
video_data = requests.get(url=photoUrl).content
with open(f'video/{caption}.mp4', mode='wb') as f: f.write(video_data) print(caption, '下载完成!')
def get_page(pcursor): # 需要的数据得指定好 # 递归, 自己调用自己 跳出递归 data = { 'operationName': "visionProfilePhotoList", 'query': "query visionProfilePhotoList($pcursor: String, $userId: String, $page: String, $webPageArea: String) {\n visionProfilePhotoList(pcursor: $pcursor, userId: $userId, page: $page, webPageArea: $webPageArea) {\n result\n llsid\n webPageArea\n feeds {\n type\n author {\n id\n name\n following\n headerUrl\n headerUrls {\n cdn\n url\n __typename\n }\n __typename\n }\n tags {\n type\n name\n __typename\n }\n photo {\n id\n duration\n caption\n likeCount\n realLikeCount\n coverUrl\n coverUrls {\n cdn\n url\n __typename\n }\n photoUrls {\n cdn\n url\n __typename\n }\n photoUrl\n liked\n timestamp\n expTag\n animatedCoverUrl\n stereoType\n videoRatio\n profileUserTopPhoto\n __typename\n }\n canAddComment\n currentPcursor\n llsid\n status\n __typename\n }\n hostName\n pcursor\n __typename\n }\n}\n", 'variables': {'userId': "3xauthkq46ftgkg", 'pcursor': pcursor, 'page': "profile"} } if pcursor == None: print('全部下载完成') return 0 get_page(pcursor) get_page('')