您好,登錄后才能下訂單哦!
利用python怎么爬取抖音視頻?針對這個問題,這篇文章詳細介紹了相對應(yīng)的分析和解答,希望可以幫助更多想解決這個問題的小伙伴找到更簡單易行的方法。
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(wù)
再點擊Start Session即可啟動Android手機上的抖音app并進入到啟動頁面
3、python腳本來驅(qū)動app,直接在pycharm運行即可
實例擴展:
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) # 獲取用戶視頻的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) # 用戶id requests.packages.urllib3.disable_warnings() self.session = requests.Session() self.target_folder = '' # 創(chuàng)建文件的路徑 self.queue = queue.Queue() # 生成一個隊列對象 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 } # 獲取下載視頻的列表 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])) # 拼接參數(shù) 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) # 視頻的名字 video_url = aweme.get('video', None).get('play_addr', None).get( 'url_list', None)[0].replace('playwm', 'play') # 視頻鏈接 self.queue.put((video_name, video_url)) # 將數(shù)據(jù)進隊列 if contentJson.get('has_more') == 1: # 判斷后面是不是還有是1就是還有 return get_aweme_list(contentJson.get('max_cursor')) # 有的話獲取參數(shù)max_cursor get_aweme_list() # 下載視頻 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): # 返回迭代對象 f.write(chunk) print('下載成功') break except: print('下載失敗') times += 1 # 創(chuàng)建對應(yīng)的文件夾 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) # 短鏈接轉(zhuǎn)長地址 def get_RealAddress(self, url): if url.find('v.douyin.com') < 0: return url response = requests.get( url=url, headers=self.header, allow_redirects=False) # allow_redirects 允許跳轉(zhuǎn) return response.headers['Location'] if __name__ == '__main__': douyin = DouYin(url='http://v.douyin.com/J2B9Sk/') douyin.user_info() douyin.get_download()
關(guān)于利用python怎么爬取抖音視頻問題的解答就分享到這里了,希望以上內(nèi)容可以對大家有一定的幫助,如果你還有很多疑惑沒有解開,可以關(guān)注億速云行業(yè)資訊頻道了解更多相關(guān)知識。
免責(zé)聲明:本站發(fā)布的內(nèi)容(圖片、視頻和文字)以原創(chuàng)、轉(zhuǎn)載和分享為主,文章觀點不代表本網(wǎng)站立場,如果涉及侵權(quán)請聯(lián)系站長郵箱:is@yisu.com進行舉報,并提供相關(guān)證據(jù),一經(jīng)查實,將立刻刪除涉嫌侵權(quán)內(nèi)容。