上一篇对b站的视频评论爬取进行了探讨,这一篇是弹幕。直接上代码:
import csv
import json
import re
import chardet
import requestsheaders = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36 SLBrowser/8.0.1.3162 SLBChan/105'}# 对爬取的页面内容进行json格式处理
def get_text(url):res = requests.get(url=url, headers=headers)res.encoding = chardet.detect(res.content)['encoding'] # 统一字符编码res = res.textdata = json.loads(res) # json格式化return datadef get_cid(bv):url_1 = 'https://api.bilibili.com/x/player/pagelist?bvid={}'.format(bv)response = get_text(url_1)cid = response['data'][0]['cid'] # 获取cidreturn ciddef get_content_list(cid):content_list = []url = f'https://comment.bilibili.com/{cid}.xml'r2 = requests.ge