爬取新闻列表

 

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

gzccurl='http://news.gzcc.cn/html/xiaoyuanxinwen/'
res=requests.get(gzccurl)
res.encoding='utf-8'
soup = BeautifulSoup(res.text,'html.parser')
li =soup.select('li')

def getclick(newsurl):
    id=re.search('_(.*).html',newsurl).group(1).split('/')[1]
    clickurl='http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(id)
    click=int(requests.get(clickurl).text.split('.')[-1].lstrip("html('").rstrip("');"))
    return click

def getonepage(listurl):
    for news in soup.select('li'):
        if len(news.select('.news-list-title'))>0:
            title=news.select('.news-list-title')[0].text
            url=news.select('a')[0]['href']
            time=news.select('.news-list-info')[0].contents[0].text
            dt=datetime.strptime(time,'%Y-%m-%d')
            source=news.select('.news-list-info')[0].contents[1].text

            resd=requests.get(url)
            resd.encoding='utf-8'
            soupd=BeautifulSoup(resd.text,'html.parser')
            detail=soupd.select('.show-content')[0].text
            click=getclick(url)
            print(time,title,dt,source,click)
            
getonepage(li)

pages=int(soup.select('.a1')[0].text.rstrip('条'))//10+1

for i in range(2,pages+1):
    url_page="http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html".format(i)
    res_page=requests.get(url_page)
    res_page.encoding='utf-8'
    soup_page=BeautifulSoup(res.text,'html.parser')
    list_page=soup.select('li')
    getonepage(list_page)