APP爬虫之B站app爬虫模板

import urllib.request
import urllib.parse
import json

# 解决证书信任问题
import ssl
ssl._create_default_https_context = ssl._create_unverified_context

# headers 通过具体抓包设置
headers ={}

video_page_num = 1
while True:
    video_page_url = ""
    """
    很漂亮的爬虫语句
    urllib.request.Request(url, headers) 
    urllib.request.urlopen(...)
    .read()
    .decode("utf-8")
    json.loads(...)
    """
    temp_data = json.loads(urllib.request.urlopen(urllib.request.Request(url=video_page_url, headers=headers)).read().decode("utf-8"))["data"]

    for eve_video in temp_data:
        oid_data = eve_video["param"]
        page_num = 1
        while True:

            comment_url = ""
            comment_data = json.loads(urllib.request.urlopen(urllib.request.Request(url=comment_url, headers=headers)).read().decode("utf-8"))
            acount = int(comment_data["data"]["page"]["acount"])

            if int(acount/20) + 1 <= page_num:
                break
            else:
                page_num = page_num + 1
            for eve_comment in comment_data["data"]["replies"]:
                eve_comment["video_data"] = eve_video
                print(eve_comment)

    if len(temp_data) < 50:
        break
    else:
        video_page_num = video_page_num + 1