标题、作者、发布单位、审核、来源
发布时间:转换成datetime类型
点击:
- newsUrl
- newsId(使用正则表达式re)
- clickUrl(str.format(newsId))
- requests.get(clickUrl)
- newClick(用字符串处理,或正则表达式)
- int()
- 主要代码如下:
-
# -*- coding: utf-8 -*- import re import requests from bs4 import BeautifulSoup from datetime import datetime def click(url): clickurl='http://oa.gzcc.cn/api.php?op=count&id=&modelid=80' res=requests.get(clickurl) click=res.text.split('.html')[-1].lstrip("('").rstrip("');") return click def newsnum(url): newsid=re.match('http://news.gzcc.cn/html/2019/xiaoyuanxinwen_0320/(.*).html',url).group(1) return newsid def newstime(url,soup): ''' time=soup.select('.show-info')[0].text[5:24] time=soup.select('.show-info')[0].text.split()[0].lstrip('发布的时间为') ''' newsdate=soup.select('.show-info')[0].text.split()[0].split(':')[1] newstime=soup.select('.show-info')[0].text.split()[1] time=newsdate+' '+newstime time=datetime.strptime(time,'%Y-%m-%d %H:%M:%S') return time def news(url): res=requests.get(url) res.encoding='utf-8' soup=BeautifulSoup(res.text,'html.parser') title=soup.select('.show-title')[0].text author=soup.select('.show-info')[0].text.split()[2] auditor=soup.select('.show-info')[0].text.split()[3] comefrom=soup.select('.show-info')[0].text.split()[4] detail=soup.select('.show-content p')[0].text newsid=newsnum(url) time=newstime(url,soup) clicktime=click(url) p=print(newsid,title,time,author,auditor,comefrom,detail,clicktime) return p url="http://news.gzcc.cn/html/2019/xiaoyuanxinwen_0320/11029.html" news(url)
效果运行如下: