import requests import requests import pprint import json import re import pprint import requests import pprint import json import re import json import requests import pprint import json import re

headers = { # data內容類型# application/json: 傳入json類型數據json 瀏覽器跟快手服務器交流(數據傳輸格式)的方式# 默認格式: application/x-www-form-urlencoded 'content-type': 'application/json', # cookie: 用戶身份標識有沒有登錄'Cookie': 'did=web_53827e0b098c608bc6f42524b1f3211a; didv=1617281516668; kpf=PC_WEB; kpn=KUAISHOU_VISION; clientid=3', # User-Agent: 瀏覽器訊息(用來偽裝成瀏覽器) 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36', } data = { 'operationName': "visionSearchPhoto",'query': "query visionSearchPhoto($keyword: String, $pcursor: String, $searchSessionId: String, $page: String, $webPageArea: String) {n visionSearchPhoto(keyword: $keyword, pcursor: $pcursor, searchSessionId: $searchSessionId, page: $page, webPageArea: $webPageArea) {n resultn llsidn webPageArean feeds {n typen author {n idn namen followingn headerUrln headerUrls {n cdnn urln __typenamen }n __typenamen }n tags {n typen namen __typenamen }n photo {n idn durationn captionn likeCountn realLikeCountn coverUrln photoUrln likedn timestampn expTagn coverUrls {n cdnn urln __typenamen }n photoUrls {n cdnn urln __typenamen }n animatedCoverUrln stereoTypen videoRation __typenamen }n canAddCommentn currentPcursorn llsidn statusn __typenamen }n searchSessionIdn pcursorn aladdinBanner {n imgUrln linkn __typenamen }n __typenamen }n}n", 'variables': { 'keyword': keyword, 'pcursor': str(page), 'page': "search" # 發送請求response = requests.p ost('https://www.kuaishou.com/graphql', headers=headers, data=data)

for page in range(0, 11): for page in range(0, 11): print(f'-----------------------正在爬取{page+1}页----------------------') json_data = response.json() data_list = json_data['data']['visionSearchPhoto']['feeds'] for data in data_list: title = data['photo']['caption'] url_1 = data['photo']['photoUrl'] new_title = re.sub(r'[/:*?"<>|n]', '_', title) # print(title, url_1) # content: 获取到的二进制数据# 文字text # 图片视频音频二进制数据content = requests.get(url_1).content print(f'-----------------------正在爬取{page+1}頁----------------------') for page in range(0, 11): print(f'-----------------------正在爬取{page+1}页----------------------') json_data = response.json() data_list = json_data['data']['visionSearchPhoto']['feeds'] for data in data_list: title = data['photo']['caption'] url_1 = data['photo']['photoUrl'] new_title = re.sub(r'[/:*?"<>|n]', '_', title) # print(title, url_1) # content: 获取到的二进制数据# 文字text # 图片视频音频二进制数据content = requests.get(url_1).content json_data = response.json() for page in range(0, 11): print(f'-----------------------正在爬取{page+1}页----------------------') json_data = response.json() data_list = json_data['data']['visionSearchPhoto']['feeds'] for data in data_list: title = data['photo']['caption'] url_1 = data['photo']['photoUrl'] new_title = re.sub(r'[/:*?"<>|n]', '_', title) # print(title, url_1) # content: 获取到的二进制数据# 文字text # 图片视频音频二进制数据content = requests.get(url_1).content data_list = json_data['data']['visionSearchPhoto']['feeds'] for page in range(0, 11): print(f'-----------------------正在爬取{page+1}页----------------------') json_data = response.json() data_list = json_data['data']['visionSearchPhoto']['feeds'] for data in data_list: title = data['photo']['caption'] url_1 = data['photo']['photoUrl'] new_title = re.sub(r'[/:*?"<>|n]', '_', title) # print(title, url_1) # content: 获取到的二进制数据# 文字text # 图片视频音频二进制数据content = requests.get(url_1).content for data in data_list: for page in range(0, 11): print(f'-----------------------正在爬取{page+1}页----------------------') json_data = response.json() data_list = json_data['data']['visionSearchPhoto']['feeds'] for data in data_list: title = data['photo']['caption'] url_1 = data['photo']['photoUrl'] new_title = re.sub(r'[/:*?"<>|n]', '_', title) # print(title, url_1) # content: 获取到的二进制数据# 文字text # 图片视频音频二进制数据content = requests.get(url_1).content title = data['photo']['caption'] for page in range(0, 11): print(f'-----------------------正在爬取{page+1}页----------------------') json_data = response.json() data_list = json_data['data']['visionSearchPhoto']['feeds'] for data in data_list: title = data['photo']['caption'] url_1 = data['photo']['photoUrl'] new_title = re.sub(r'[/:*?"<>|n]', '_', title) # print(title, url_1) # content: 获取到的二进制数据# 文字text # 图片视频音频二进制数据content = requests.get(url_1).content url_1 = data['photo']['photoUrl'] for page in range(0, 11): print(f'-----------------------正在爬取{page+1}页----------------------') json_data = response.json() data_list = json_data['data']['visionSearchPhoto']['feeds'] for data in data_list: title = data['photo']['caption'] url_1 = data['photo']['photoUrl'] new_title = re.sub(r'[/:*?"<>|n]', '_', title) # print(title, url_1) # content: 获取到的二进制数据# 文字text # 图片视频音频二进制数据content = requests.get(url_1).content new_title = re.sub(r'[/:*?"<>|n]', '_', title) for page in range(0, 11): print(f'-----------------------正在爬取{page+1}页----------------------') json_data = response.json() data_list = json_data['data']['visionSearchPhoto']['feeds'] for data in data_list: title = data['photo']['caption'] url_1 = data['photo']['photoUrl'] new_title = re.sub(r'[/:*?"<>|n]', '_', title) # print(title, url_1) # content: 获取到的二进制数据# 文字text # 图片视频音频二进制数据content = requests.get(url_1).content # print(title, url_1) for page in range(0, 11): print(f'-----------------------正在爬取{page+1}页----------------------') json_data = response.json() data_list = json_data['data']['visionSearchPhoto']['feeds'] for data in data_list: title = data['photo']['caption'] url_1 = data['photo']['photoUrl'] new_title = re.sub(r'[/:*?"<>|n]', '_', title) # print(title, url_1) # content: 获取到的二进制数据# 文字text # 图片视频音频二进制数据content = requests.get(url_1).content # content: 獲取到的二進制數據# 文字text for page in range(0, 11): print(f'-----------------------正在爬取{page+1}页----------------------') json_data = response.json() data_list = json_data['data']['visionSearchPhoto']['feeds'] for data in data_list: title = data['photo']['caption'] url_1 = data['photo']['photoUrl'] new_title = re.sub(r'[/:*?"<>|n]', '_', title) # print(title, url_1) # content: 获取到的二进制数据# 文字text # 图片视频音频二进制数据content = requests.get(url_1).content

with open('./video/' + new_title + '.mp4', mode='wb') as f: with open('./video/' + new_title + '.mp4', mode='wb') as f: f.write(content) print(new_title, '爬取成功!!!') f.write(content) with open('./video/' + new_title + '.mp4', mode='wb') as f: f.write(content) print(new_title, '爬取成功!!!')