爬取虎牙TV全站主播信息

"""
Created by Young on 2019/1/16 17:00
"""

from bs4 import BeautifulSoup
import requests
import json as js
import re


headers = {'user-agent':''}

#之前爬取错了,这个只能爬取一页
def parsing_webpage(url):
    wb_data = requests.get(url,headers=headers)
    wb_data.encoding = "utf-8"  #解决乱码
    soup = BeautifulSoup(wb_data.text,'lxml',from_encoding="utf8")
    rooms = soup.find('ul',class_='live-list clearfix')
    single_rooms = rooms.find_all('li',class_='game-live-item')
    for single_room in single_rooms:
        room_title = single_room.find_all('a',class_='title new-clickstat')[0].get_text()
        nick_title = single_room.find_all('i',class_='nick')[0].get_text()
        room_popularity = single_room.find_all('i',class_='js-num')[0].get_te