python爬取抖音視訊的例項分析
阿新 • • 發佈:2021-01-21
現在抖音的火爆程度,大家都是有目共睹的吧,之前小編在網路上發現好玩的事情,就是去爬取一些網站,因此,也考慮能否進行抖音上的破案去,在實際操作以後,真的實現出來了,利用自動化工具,就可以輕鬆實現了,後有小夥伴提出把appium去掉瘦身之後也是可以實現的,那麼看下詳細操作內容吧。
1、mitmproxy/mitmdump抓包
import requests path = 'D:/video/' num = 1788 def response(flow): global num target_urls = ['url'] for url in target_urls: if flow.request.url.startswith(url): filename = path + str(num) + '.mp4 res = requests.get(flow.request.url,stream=True) with open(filename,'ab') as f: f.write(res.content) f.flush() print(filename + '下載完成') num += 1
2、Appium對手機進行模擬操作
利用Start Server按鈕即可啟動appium服務
再點選Start Session即可啟動Android手機上的抖音app並進入到啟動頁面
3、python指令碼來驅動app,直接在pycharm執行即可
例項擴充套件:
import requests import json import re import os from pprint import pprint as pp import queue class DouYin: header = { 'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8','accept-encoding': 'gzip,deflate,br','accept-language': 'zh-CN,zh;q=0.9','cache-control': 'max-age=0','upgrade-insecure-requests': '1','user-agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 11_0 like Mac OS X) AppleWebKit/604.1.38 (KHTML,like Gecko) Version/11.0 Mobile/15A372 Safari/604.1',} def __init__(self,url=None): self.url = self.get_RealAddress(url) # 獲取使用者視訊的url self.user_video_url = 'https://www.douyin.com/aweme/v1/aweme/post/?{0}' self.user_id = re.search(r'user/(.*)\?',self.url).group(1) # 使用者id requests.packages.urllib3.disable_warnings() self.session = requests.Session() self.target_folder = '' # 建立檔案的路徑 self.queue = queue.Queue() # 生成一個佇列物件 def user_info(self): self.mkdir_dir() p = os.popen('node fuck.js %s' % self.user_id) # 獲取加密的signature signature = p.readlines()[0] user_video_params = { 'user_id': str(self.user_id),'count': '21','max_cursor': '0','aid': '1128','_signature': signature } # 獲取下載視訊的列表 def get_aweme_list(max_cursor=None): if max_cursor: user_video_params['max_cursor'] = str(max_cursor) user_video_url = self.user_video_url.format( '&'.join([key + '=' + user_video_params[key] for key in user_video_params])) # 拼接引數 response = requests.get( url=user_video_url,headers=self.header,verify=False) contentJson = json.loads(response.content.decode('utf-8')) # 將返回的進行utf8編碼 aweme_list = contentJson.get('aweme_list',[]) for aweme in aweme_list: video_name = aweme.get( 'share_info',None).get('share_desc',None) # 視訊的名字 video_url = aweme.get('video',None).get('play_addr',None).get( 'url_list',None)[0].replace('playwm','play') # 視訊連結 self.queue.put((video_name,video_url)) # 將資料進佇列 if contentJson.get('has_more') == 1: # 判斷後面是不是還有是1就是還有 return get_aweme_list(contentJson.get('max_cursor')) # 有的話獲取引數max_cursor get_aweme_list() # 下載視訊 def get_download(self): while True: video_name,video_url = self.queue.get() file_name = video_name + '.mp4' file_path = os.path.join(self.target_folder,file_name) if not os.path.isfile(file_path): print('download %s form %s.\n' % (file_name,video_url)) times = 0 while times < 10: try: response = requests.get( url=video_url,stream=True,timeout=10,verify=False) # 開啟流下載 with open(file_path,'wb') as f: for chunk in response.iter_content(1024): # 返回迭代物件 f.write(chunk) print('下載成功') break except: print('下載失敗') times += 1 # 建立對應的資料夾 def mkdir_dir(self): current_folder = os.getcwd() self.target_folder = os.path.join( current_folder,'download/%s' % self.user_id) if not os.path.isdir(self.target_folder): os.mkdir(self.target_folder) # 短連結轉長地址 def get_RealAddress(self,url): if url.find('v.douyin.com') < 0: return url response = requests.get( url=url,allow_redirects=False) # allow_redirects 允許跳轉 return response.headers['Location'] if __name__ == '__main__': douyin = DouYin(url='http://v.douyin.com/J2B9Sk/') douyin.user_info() douyin.get_download()
到此這篇關於python爬取抖音視訊的例項分析的文章就介紹到這了,更多相關如何使用python爬取抖音視訊內容請搜尋我們以前的文章或繼續瀏覽下面的相關文章希望大家以後多多支援我們!