python3爬取新浪新闻文章内容代码

import pandas as pd
import requests
import json
from bs4 import BeautifulSoup
from datetime import datetime
import re

#当页跳转url
url = 'http://api.roll.news.sina.com.cn/zt_list?channel=news&cat_1=gnxw&cat_2==gdxw1||=gatxw||=zs-pl||=mtjj&level==1||=2&show_ext=1&show_all=1&show_num=22&tag=1&format=json&page={}'
url.encode('utf-8')
# #形成多页链接，并且解析每页的所有链接及每个链接的内容详情

#该篇文章评论url
commenturl = 'http://comment5.news.sina.com.cn/page/info?version=1&format=json&channel=sh&newsid=comos-{}&group=undefined&compress=0&ie=utf-8&oe=utf-8&page=1&page_size=3'


##获取评论总数函数
def getcomments(newsurl):
    m=re.search('doc-i(.*).shtml',newsurl)
    newsid=m.group(1)
    comments = requests.get(commenturl.format(newsid))
    jd1 = json.loads(c