crawl-bilibili/user/main.py

# -*- coding: utf-8 -*-
'''
@Auther :liuyuqi.gov@msn.cn
@date :2019/4/8
'''
__author__ = "liuyuqi"

import json
import os
import re
from contextlib import closing

import requests

import DownloadProgress
import user_agent

# src = "D:/PycharmProjects/crawl_xuexi/"
# os.chdir(src)



def crawl():
    with open("data/ml.json", "r", encoding="utf8") as f:
        mlData = json.loads(f.read())
        for i in range((len(mlData["fpe1ki18v228w00"]))):
            frst_name = mlData["fpe1ki18v228w00"][i]["frst_name"].replace('\t', ' ')
            static_page_url = mlData["fpe1ki18v228w00"][i]["static_page_url"]
            # 打开 mp4 视频网页链接
            resData = requests.get(static_page_url, headers=user_agent.getheaders()).content.decode("utf8")
            preUrl = static_page_url.split("/")[3]
            pattern = r'src="./data(.*?)"></script>'
            url = "https://www.xuexi.cn/" + preUrl + "/data" + re.findall(pattern, resData, re.I)[0]
            res = get_video_links(url)[0]
            downloadVideo(res, file_name=frst_name)


if __name__ == '__main__':
    crawl()