17/10/18

import requests
import re
import pandas
from bs4 import BeautifulSoup
def getclick(newurl): #函数：采用匹配方式，动态获取每一文章点击次数
id=re.search('_(.*).html',newurl).group(1).split('/')[1]
clickurl='http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(id)
click=int(requests.get('http://oa.gzcc.cn/api.php?op=count&id=4662&modelid=80').text.split('.')[-1].lstrip("html('").rstrip("');"))
return int(click)

def getdetail(url):#给定网址，出来正文，形式是字典
resd=requests.get(url)
resd.encoding='utf-8'
soupd=BeautifulSoup(resd.text,'html.parser')
news={}
news['url']=url
news['title']=soupd.select('.show-title')[0].text #标题
info=soupd.select('.show-info')[0].text #标题
#news['dt']=datetime.strptime(info.lstrip('发布时间：')[0:19],'%Y-%m-%d %H:%M'
#news['source']=re.search('来源：_(.*).点击',info).group(1).split()
news['click']=getclick(url)
return(news)

def onepage(pageurl):
res=requests.get(pageurl)
res.encoding='utf-8'
soup=BeautifulSoup(res.text,'html.parser')
newsls=[]
for news in soup.select('li'):
if len(news.select('.news-list-title'))>0:
newsls.append(getdetail(news.select('a')[0]['href']))
return(newsls)
print(onepage('http://news.gzcc.cn/html/xiaoyuanxinwen/'))

 

newstotal=[]
gzcc='http://news.gzcc.cn/html/xiaoyuanxinwen/'
newstotal.extend(onepage(gzcc))
res=requests.get(gzcc)
res.encoding='utf-8'
soup=BesutifulSoup(res.text,'html.parser')
n=int(soup.select('.a1')[0].text.rstrip('条'))
pages=n//10+1 #计算多少条多少页

for i in range(2,3):
    listurl='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
    newstotal.extend(onepage(listurl))
df=pandas.DataFrame(newtotal)
df.to_execl(gzccnews.xlsx)