爬取所有校园新闻

from datetime import datetime
import requests
from bs4 import BeautifulSoup
import re
html=‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘
res = requests.get(html)
res.encoding=‘utf-8‘
soup = BeautifulSoup(res.text,‘html.parser‘)
def getdetail(htm):
    resd = requests.get(htm)
    resd.encoding=‘utf-8‘
    soupd = BeautifulSoup(resd.text,‘html.parser‘)
    return soupd.select(‘.show-content‘)[0].text
def getclick(newsurl):
    id =re.match(‘http://news.gzcc.cn/html/2017/xiaoyuanxinwen_(.*).html‘,newsurl).groups()[0].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)
for news in soup.select(‘li‘):
     if len(news.select(‘.news-list-title‘))>0:
         htm = news.select(‘a‘)[0][‘href‘]
         print (news.select(‘a‘)[0][‘href‘])
         print (news.select(‘.news-list-title‘)[0].text)
         time=news.select(‘.news-list-info‘)[0].contents[0].text
         print (datetime.strptime(time,‘%Y-%m-%d‘))
         print (news.select(‘.news-list-info‘)[0].contents[1].text)
         detail =  getdetail(htm)
         click=getclick(htm)
         print(detail)
         print(click)
  
    #click=requests.get(‘http://oa.gzcc.cn/api.php?op=count&id=8249&modelid=80‘).text.split(‘.‘)[-1].lstrip("html(‘").rstrip("‘);")
    #print (click)

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


def getclick(newsurl):
    id =re.match(‘http://news.gzcc.cn/html/2017/xiaoyuanxinwen_(.*).html‘,newsurl).groups()[0].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 getdetail(listurl):
    resd = requests.get(listurl)
    resd.encoding=‘utf-8‘
    soupd = BeautifulSoup(resd.text,‘html.parser‘)
    soupd.select(‘.show-content‘)[0].text
    for news in soup.select(‘li‘):
        if len(news.select(‘.news-list-title‘))>0:
           h = news.select(‘a‘)[0][‘href‘]
           print (news.select(‘a‘)[0][‘href‘])
           print (news.select(‘.news-list-title‘)[0].text)
           time=news.select(‘.news-list-info‘)[0].contents[0].text
           print (datetime.strptime(time,‘%Y-%m-%d‘))
           print (news.select(‘.news-list-info‘)[0].contents[1].text)
           detail = soupd.select(‘.show-content‘)[0].text
           click=getclick(h)
           print(detail)
           print(click)
getdetail=(‘http://news.gzcc.cn/html/xiaoyuanxinwen/index.html‘) 
res = requests.get("http://news.gzcc.cn/html/xiaoyuanxinwen/")
res.encoding=‘utf-8‘
soup = BeautifulSoup(res.text,‘html.parser‘)
pages=int(soup.select(‘.a1‘)[0].text.rstrip(‘条‘))//10+1  #计算页
print (pages)
for i in range(2,5):
    list=‘http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html‘.format(i)
    getdetail(list)