利用av号爬取Bilibili视频弹幕

#bilibili弹幕抓取
import requests
import re
from bs4 import BeautifulSoup
import operator#排序
 
def getHTMLText(url):
    try:
        print("获取url中...")
        headers = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.62 Safari/537.36'}
        r = requests.get(url,headers=headers)
        print("获取url完成")
        return r.text
    except:
        print("获取Url失败")
        
def parsePage(text):
    try:
        print("解析文本...")
        keyStr = re.findall(r'upgcxcode/78/39/[\d]*',text)#B站有两种寻址方式，第二种多一些
        key = eval(keyStr[0].split('/')[3])
        print(key)
        commentUrl = 'https://api.bilibili.com/x/v1/dm/list.so?oid=' + str(key)  # 弹幕存储地址
        res=requests.get(commentUrl)
        res.encoding = 'utf-8'
        commentText=res.text
        soup = Beautiful