python爬虫——获取新浪新闻前两页新闻信息

import requests
import json
from bs4 import BeautifulSoup
import re
import json
from datetime import datetime

commentURL='http://comment5.news.sina.com.cn/page/info?version=1&\
                 format=js&channel=sh&newsid=comos-{}&\
                 group=&compress=0&ie=utf-8&oe=utf-8&page=1&\
                 page_size=20'
def getCommentCount(newsurl):
    m=re.search('doc-i(.+).shtml',newsurl)
    newsid=m.group(1)
    comments=requests.get(commentURL.format(newsid))
    jd=json.loads(comments.text.strip('var data='))
    return jd['result']['count']['total']

def getNewsDetail(newsurl):
    result={}
    res=requests.get(newsurl)
    res.encoding='utf-8'
    soup=BeautifulSoup(res.text,'html.parser')
    result['title']=soup.select('#artibodyTitle')[0].text
    result['newssource']=soup.select('.time-source span a')[0].text
    timesource=soup.select('.time-source')[0].contents[0].strip()
    result['dt']=datetime.strptime(timesource,'%Y年%m月%d日%H:%M')
    result['article']=' '.join([p.text.strip() for p in soup.select('#artibody p')[:-1]])
    result['editor']=soup.select('.show_author')[0].text.lstrip('责任编辑：')
    result['comments']=getCommentCount(newsurl)
    return result
#news='http://news.sina.com.cn/c/nd/2017-12-09/doc-ifypnyqi2478315.shtml'
#print(getNewsDetail(news))

def parserlistlinks(url):
    newsdetails=[]
    res=requests.get(url)
    jd=json.loads(res.text.lstrip('  newsloadercallback(').rstrip(');'))
    for ent in jd['result']['data']:
        newsdetails.append(getNewsDetail(ent['url']))
    return newsdetails
#news='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=2&callback=newsloadercallback&_=1512876098022'
#print(parserlistlinks(news))

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={}&callback=newsloadercallback&_=1512876098022'
news_total=[]
for i in range(1,3):
    newsurl=url.format(i)
    newsary=parserlistlinks(newsurl)
    news_total.extend(newsary)
    print(news_total)
#print(len(news_total))
'''
import pandas
df=pandas.DataFrame(news_total)
#print(df.head(2))
print(df.to_excel('news.xlsx'))
'''