简单爬虫案例——爬取快手视频_业界新闻

import requests import re url = 'https://www.kuaishou.com/graphql' cookies = { 'did': 'web_9e8cfa4403000587b9e7d67233e6b04c', 'didv': '1719811812378', 'kpf': 'PC_WEB', 'clientid': '3', 'kpn': 'KUAISHOU_VISION', } headers = { 'Accept-Language': 'zh-CN,zh;q=0.9', 'Cache-Control': 'no-cache', 'Connection': 'keep-alive', # 'Cookie': 'did=web_9e8cfa4403000587b9e7d67233e6b04c; didv=1719811812378; kpf=PC_WEB; clientid=3; kpn=KUAISHOU_VISION', 'Origin': 'https://www.kuaishou.com', 'Pragma': 'no-cache', 'Referer': 'https://www.kuaishou.com/search/video?searchKey=%E6%8B%89%E9%9D%A2', 'Sec-Fetch-Dest': 'empty', 'Sec-Fetch-Mode': 'cors', 'Sec-Fetch-Site': 'same-origin', 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36', 'accept': '*/*', 'content-type': 'application/json', 'sec-ch-ua': '"Not/A)Brand";v="8", "Chromium";v="126", "Google Chrome";v="126"', 'sec-ch-ua-mobile': '?0', 'sec-ch-ua-platform': '"Windows"', } json_data = { 'operationName': 'visionSearchPhoto', 'variables': { 'keyword': '拉面', 'pcursor': '', 'page': 'search', }, 'query': 'fragment photoContent on PhotoEntity {\n __typename\n id\n duration\n caption\n originCaption\n likeCount\n viewCount\n commentCount\n realLikeCount\n coverUrl\n photoUrl\n photoH265Url\n manifest\n manifestH265\n videoResource\n coverUrls {\n url\n __typename\n }\n timestamp\n expTag\n animatedCoverUrl\n distance\n videoRatio\n liked\n stereoType\n profileUserTopPhoto\n musicBlocked\n riskTagContent\n riskTagUrl\n}\n\nfragment recoPhotoFragment on recoPhotoEntity {\n __typename\n id\n duration\n caption\n originCaption\n likeCount\n viewCount\n commentCount\n realLikeCount\n coverUrl\n photoUrl\n photoH265Url\n manifest\n manifestH265\n videoResource\n coverUrls {\n url\n __typename\n }\n timestamp\n expTag\n animatedCoverUrl\n distance\n videoRatio\n liked\n stereoType\n profileUserTopPhoto\n musicBlocked\n riskTagContent\n riskTagUrl\n}\n\nfragment feedContent on Feed {\n type\n author {\n id\n name\n headerUrl\n following\n headerUrls {\n url\n __typename\n }\n __typename\n }\n photo {\n ...photoContent\n ...recoPhotoFragment\n __typename\n }\n canAddComment\n llsid\n status\n currentPcursor\n tags {\n type\n name\n __typename\n }\n __typename\n}\n\nquery visionSearchPhoto($keyword: String, $pcursor: String, $searchSessionId: String, $page: String, $webPageArea: String) {\n visionSearchPhoto(keyword: $keyword, pcursor: $pcursor, searchSessionId: $searchSessionId, page: $page, webPageArea: $webPageArea) {\n result\n llsid\n webPageArea\n feeds {\n ...feedContent\n __typename\n }\n searchSessionId\n pcursor\n aladdinBanner {\n imgUrl\n link\n __typename\n }\n __typename\n }\n}\n', } response = requests.post(url=url, cookies=cookies, headers=headers, json=json_data) for index in response.json()['data']['visionSearchPhoto']['feeds']: title = index['photo']['caption'] newtitle = re.sub(r'[\\/?<>:*|\n\r]','',title) link = index['photo']['photoUrl'] print(title,link) content = requests.get(url=link,headers=headers).content with open('快手video//'+title+'.mp4','wb') as f: f.write(content)