【Python】B站详细信息抓取

import time
import requests
import pandas as pd
import random
headers = {
    "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",
    "Referer": "https://www.bilibili.com/",
}

video_data = []
for page in range(1,2):
    api_url = f'https://api.bilibili.com/x/space/arc/search?mid=10330740&ps=30&tid=0&pn={page}&keyword=&order=pubdate&jsonp=jsonp'
    res = requests.get(api_url, headers=headers).json()
    video_list = res['data']['list']['vlist']
    for video in video_list:
        videos_dic = {}
        videos_dic["title"]=video['title']
        videos_dic["img"] = video["pic"]
        videos_dic['video_time'] = video['length']
        videos_dic['play_num'] = video['play']
        videos_dic['video_description'] = video['description']
        videos_dic['author'] = video['author']
        videos_dic['comment_num'] = video['comment']
        videos_dic['play_url'] = 'https://www.bilibili.com/video/' + video['bvid']
        video_data.append(videos_dic)
    time.sleep(random.randint(2, 5))

video_df = pd.DataFrame(video_data)