spider-bilibili

?

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58

# 话不多说，直接上源码<br>import urllib, requests import urllib.request as req import re import json import subprocess   headers = {     'user-agent': 'Mozilla/5.0 (Windows NT 10.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.112 Safari/537.36',     'referer': 'https://www.bilibili.com/' }   video_path = './video/' movie_path = './movie/' def get_html_data(url_path):       data_html = requests.get(url_path, headers=headers, proxies=proxies).text     return data_html     def get_download_url():     url = 'https://www.bilibili.com/video/av288087621/'     data_html = get_html_data(url)     title = re.findall('<span class="tit">(.*?)</span>', data_html)[0]     json_data = re.findall('<script>window\.__playinfo__=(.*?)</script>', data_html)[0]     json_data = json.loads(json_data)     video_url = json_data['data']['dash']['audio'][0]['backupUrl'][0]     movie_url = json_data['data']['dash']['video'][0]['backupUrl'][0]     download_data(title, video_url, movie_url)     def download_data(title, video_url, movie_url):     # 下载音频数据     video_data = requests.get(video_url, headers=headers, proxies=proxies).content       # 下载视频数据     movie_data = requests.get(movie_url, headers=headers, proxies=proxies).content     local_save_data(title, video_data, movie_data)     def local_save_data(title, video_data, movie_data):     # 保存音频数据     with open(video_path + title + '.mp3', 'wb') as w:         w.write(video_data)       # 保存视频数据     with open(movie_path + title + '.mp4', 'wb') as w:         w.write(movie_data)       merge_data(title)   def merge_data(title):     print("视频合成开始：%s" % title)     COMMAND = f"ffmpeg -i {movie_path + title}.mp4 -i {video_path + title}.mp3 -c:v copy -c:a aac -strict experimental {movie_path}output.mp4"     subprocess.Popen(COMMAND, shell=True)     print("视频合成结束：%s" % title)   if __name__ == '__main__':     get_download_url()