python 爬取B站原视频的实例代码

这篇文章主要介绍了python 爬取B站原视频的实例代码，帮助大家更好的理解和使用python 爬虫,感兴趣的朋友可以了解下

B站原视频爬取，我就不多说直接上代码。直接运行就好。
B站是把视频和音频分开。要把2个合并起来使用。这个需要分析才能看出来。然后就是登陆这块是比较难的。

  1 import os
  2 import re
  3 import argparse
  4 import subprocess
  5 import prettytable
  6 from DecryptLogin import login
  7  
  8  
  9 """B站类"""
 10 class Bilibili():
 11 def __init__(self, username, password, **kwargs):
 12 self.username = username
 13 self.password = password
 14 self.session = Bilibili.login(username, password)
 15 self.headers = {
 16 "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.117 Safari/537.36"
 17 }
 18 self.user_info_url = "http://api.bilibili.com/x/space/acc/info"
 19 self.submit_videos_url = "http://space.bilibili.com/ajax/member/getSubmitVideos"
 20 self.view_url = "http://api.bilibili.com/x/web-interface/view"
 21 self.video_player_url = "http://api.bilibili.com/x/player/playurl"
 22 """运行主程序"""
 23 def run(self):
 24 while True:
 25 userid = input("请输入目标用户ID(例:345993405)(我的一个LOL好友凯撒可以关注他一下 谢谢) ——> ")
 26 user_info = self.__getUserInfo(userid)
 27 tb = prettytable.PrettyTable()
 28 tb.field_names = list(user_info.keys())
 29 tb.add_row(list(user_info.values()))
 30 print("获取的用户信息如下:")
 31 print(tb)
 32 is_download = input("是否下载该用户的所有视频(y/n, 默认: y) ——> ")
 33 if is_download == "y" or is_download == "yes" or not is_download:
 34 self.__downloadVideos(userid)
 35 """根据userid获得该用户基本信息"""
 36 def __getUserInfo(self, userid):
 37 params = {"mid": userid, "jsonp": "jsonp"}
 38 res = self.session.get(self.user_info_url, params=params, headers=self.headers)
 39 res_json = res.json()
 40 user_info = {
 41 "用户名": res_json["data"]["name"],
 42 "性别": res_json["data"]["sex"],
 43 "个性签名": res_json["data"]["sign"],
 44 "用户等级": res_json["data"]["level"],
 45 "生日": res_json["data"]["birthday"]
 46 }
 47 return user_info
 48 """下载目标用户的所有视频"""
 49 def __downloadVideos(self, userid):
 50 if not os.path.exists(userid):
 51 os.mkdir(userid)
 52 # 非会员用户只能下载到高清1080P
 53 quality = [("16", "流畅 360P"),
 54 ("32", "清晰 480P"),
 55 ("64", "高清 720P"),
 56 ("74", "高清 720P60"),
 57 ("80", "高清 1080P"),
 58 ("112", "高清 1080P+"),
 59 ("116", "高清 1080P60")][-3]
 60 # 获得用户的视频基本信息
 61 video_info = {"aids": [], "cid_parts": [], "titles": [], "links": [], "down_flags": []}
 62 params = {"mid": userid, "pagesize": 30, "tid": 0, "page": 1, "order": "pubdate"}
 63 while True:
 64 res = self.session.get(self.submit_videos_url, headers=self.headers, params=params)
 65 res_json = res.json()
 66 for item in res_json["data"]["vlist"]:
 67 video_info["aids"].append(item["aid"])
 68 if len(video_info["aids"]) < int(res_json["data"]["count"]):
 69 params["page"] += 1
 70 else:
 71 break
 72 for aid in video_info["aids"]:
 73 params = {"aid": aid}
 74 res = self.session.get(self.view_url, headers=self.headers, params=params)
 75 cid_part = []
 76 for page in res.json()["data"]["pages"]:
 77 cid_part.append([page["cid"], page["part"]])
 78 video_info["cid_parts"].append(cid_part)
 79 title = res.json()["data"]["title"]
 80 title = re.sub(r"[‘"/:*?"<>|s"]", " ", title)
 81 video_info["titles"].append(title)
 82 print("共获取到用户ID<%s>的<%d>个视频..." % (userid, len(video_info["titles"])))
 83 for idx in range(len(video_info["titles"])):
 84 aid = video_info["aids"][idx]
 85 cid_part = video_info["cid_parts"][idx]
 86 link = []
 87 down_flag = False
 88 for cid, part in cid_part:
 89 params = {"avid": aid, "cid": cid, "qn": quality, "otype": "json", "fnver": 0, "fnval": 16}
 90 res = self.session.get(self.video_player_url, params=params, headers=self.headers)
 91 res_json = res.json()
 92 if "dash" in res_json["data"]:
 93 down_flag = True
 94 v, a = res_json["data"]["dash"]["video"][0], res_json["data"]["dash"]["audio"][0]
 95 link_v = [v["baseUrl"]]
 96 link_a = [a["baseUrl"]]
 97 if v["backup_url"]:
 98 for item in v["backup_url"]:
 99 link_v.append(item)
100 if a["backup_url"]:
101 for item in a["backup_url"]:
102 link_a.append(item)
103 link = [link_v, link_a]
104 else:
105 link = [res_json["data"]["durl"][-1]["url"]]
106 if res_json["data"]["durl"][-1]["backup_url"]:
107 for item in res_json["data"]["durl"][-1]["backup_url"]:
108 link.append(item)
109 video_info["links"].append(link)
110 video_info["down_flags"].append(down_flag)
111 # 开始下载
112 out_pipe_quiet = subprocess.PIPE
113 out_pipe = None
114 aria2c_path = os.path.join(os.getcwd(), "tools/aria2c")
115 ffmpeg_path = os.path.join(os.getcwd(), "tools/ffmpeg")
116 for idx in range(len(video_info["titles"])):
117 title = video_info["titles"][idx]
118 aid = video_info["aids"][idx]
119 down_flag = video_info["down_flags"][idx]
120 print("正在下载视频<%s>..." % title)
121 if down_flag:
122 link_v, link_a = video_info["links"][idx]
123 # --视频
124 url = ""{}"".format("" "".join(link_v))
125 command = "{} -c -k 1M -x {} -d "{}" -o "{}" --referer="https://www.bilibili.com/video/av{}" {} {}"
126 command = command.format(aria2c_path, len(link_v), userid, title+".flv", aid, "", url)
127 print(command)
128 process = subprocess.Popen(command, stdout=out_pipe, stderr=out_pipe, shell=True)
129 process.wait()
130 # --音频
131 url = ""{}"".format("" "".join(link_a))
132 command = "{} -c -k 1M -x {} -d "{}" -o "{}" --referer="https://www.bilibili.com/video/av{}" {} {}"
133 command = command.format(aria2c_path, len(link_v), userid, title+".aac", aid, "", url)
134 print(command)
135  
136 process = subprocess.Popen(command, stdout=out_pipe, stderr=out_pipe, shell=True)
137 process.wait()
138 # --合并
139 command = "{} -i "{}" -i "{}" -c copy -f mp4 -y "{}""
140 command = command.format(ffmpeg_path, os.path.join(userid, title+".flv"), os.path.join(userid, title+".aac"), os.path.join(userid, title+".mp4"))
141 print(command)
142  
143 process = subprocess.Popen(command, stdout=out_pipe, stderr=out_pipe_quiet, shell=True)
144 process.wait()
145 os.remove(os.path.join(userid, title+".flv"))
146 os.remove(os.path.join(userid, title+".aac"))
147 else:
148 link = video_info["links"][idx]
149 url = ""{}"".format("" "".join(link))
150 command = "{} -c -k 1M -x {} -d "{}" -o "{}" --referer="https://www.bilibili.com/video/av{}" {} {}"
151 command = command.format(aria2c_path, len(link), userid, title+".flv", aid, "", url)
152 process = subprocess.Popen(command, stdout=out_pipe, stderr=out_pipe, shell=True)
153 process.wait()
154 os.rename(os.path.join(userid, title+".flv"), os.path.join(userid, title+".mp4"))
155 print("所有视频下载完成, 该用户所有视频保存在<%s>文件夹中..." % (userid))
156 """借助大佬开源的库来登录B站"""
157 @staticmethod
158 def login(username, password):
159 _, session = login.Login().bilibili(username, password)
160 return session
161  
162  
163 """run"""
164 if __name__ == "__main__":
165 parser = argparse.ArgumentParser(description="下载B站指定用户的所有视频(仅支持Windows下使用)")
166 parser.add_argument("--username", dest="username", help="xxx", type=str, required=True)
167 parser.add_argument("--password", dest="password", help="xxxx", type=str, required=True)
168 print(parser)
169 args = parser.parse_args(["--password", "xxxx","--username", "xxx"])
170 # args = parser.parse_args(["--password", "FOO"])
171 print("5")
172 bili = Bilibili(args.username, args.password)
173 bili.run()