【Python爬虫】第五课（b站弹幕）

首先，非常感谢大神的文章 https://www.cnblogs.com/LexMoon/p/pyspider03.html#4361286

import requests
import re
av_id = '67946325'
headers = {
    'User-Agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',
    'Accept': 'text/html',
    'Cookie': "_uuid=1DBA4F96-2E63-8488-DC25-B8623EFF40E773841infoc; buvid3=FE0D3174-E871-4A3E-877C-A4ED86E20523155831infoc; LIVE_BUVID=AUTO8515670521735348; sid=l765gx48; DedeUserID=33717177; DedeUserID__ckMd5=be4de02fd64f0e56; SESSDATA=cf65a5e0%2C1569644183%2Cc4de7381; bili_jct=1e8cdbb5755b4ecd0346761a121650f5; CURRENT_FNVAL=16; stardustvideo=1; rpdid=|(umY))|ukl~0J'ulY~uJm)kJ; UM_distinctid=16ce0e51cf0abc-02da63c2df0b4b-5373e62-1fa400-16ce0e51cf18d8; stardustpgcv=0606; im_notify_type_33717177=0; finger=b3372c5f; CURRENT_QUALITY=112; bp_t_offset_33717177=300203628285382610"

}
resp = requests.get('https://www.bilibili.com/video/av'+av_id,headers=headers)

match_rule = r'cid=(.*?)&aid'
oid = re.search(match_rule,resp.text).group().replace('cid=','').replace('&aid','')
print('oid='+oid)

xml_url = 'https://api.bilibili.com/x/v1/dm/list.so?oid='+oid

resp = requests.get(xml_url,headers=headers)


if resp.encoding == 'ISO-8859-1':
    encodings = requests.utils.get_encodings_from_content(resp.text)
    if encodings:
        encoding = encodings[0]
    else:
        encoding = resp.apparent_encoding
    global encode_content
    encode_content = resp.content.decode(encoding,'replace')
    
print(encode_content)

#爬虫headers需要包含什么内容才不会返回404呢？我尝试7个全写，发现就不对。
#正则表达式快忘记了……
#最后的乱码解决方案

【Python爬虫】第五课（b站弹幕）

猜你喜欢