import requests from bs4 import BeautifulSoup import re url_main="http://news.gzcc.cn/html/xiaoyuanxinwen/" res = requests.get(url_main) res.encoding = ‘utf-8‘ soup = BeautifulSoup(res.text,‘html.parser‘) li = soup.select(‘li‘) #获取一个新闻列表页的所有新闻的上述详情,并包装成一个函数 def gethits(url_1): li_id =re.search(‘_.*/(.*).html‘,url_1).groups(0)[0] hits = requests.get(‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(li_id)).text.split(‘.‘)[-1].rstrip(‘‘‘‘);‘‘‘).lstrip(‘‘‘‘html(‘‘‘) return hits #获取单条新闻的#标题#链接#时间#来源#正文 #点击次数,并包装成一个函数。 def getpageinfo(label): for title_list in label: if len(title_list.select(‘.news-list-title‘))>0: href = title_list.select(‘a‘)[0][‘href‘] title = title_list.select(‘.news-list-title‘)[0].text time = title_list.select(‘span‘)[0].text info = title_list.select(‘span‘)[1].text res_list = requests.get(href) res_list.encoding = ‘utf-8‘ soup_list = BeautifulSoup(res_list.text,‘html.parser‘) zhengwen = soup_list.select(‘.show-content‘)[0].text hits_list = gethits(href) print(‘时间:‘,time,‘\n标题:‘,title,‘\n链接:‘,href,‘\n来源:‘,info,‘\n点击次数:‘,hits_list,‘\n‘) print(‘正文:‘,zhengwen) break getpageinfo(li)
4.完成所有校园新闻的爬取工作。
import requests from bs4 import BeautifulSoup import re mt="http://news.gzcc.cn/html/xiaoyuanxinwen/" res=requests.get(mt) res.encoding=‘utf-8‘ soup=BeautifulSoup(res.text,"html.parser") def getdate(newurl): id=re.search(‘_(.*).html‘,newurl).group(1).split(‘/‘)[1] dijiurl=‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(id) diji=requests.get(‘http://oa.gzcc.cn/api.php?op=count&id=8301&modelid=80‘).text.split(‘.‘)[-1].lstrip("html(‘").rstrip("html‘);") return date def genonepage(listurl): res=requests.get(listurl) res.encoding=‘utf-8‘ soup=BeautifulSoup(res.text,"html.parser") for news in soup.select(‘li‘): if len(news.select(‘.news-list-title‘))>0: sorce=(news.select(‘.news-list-info‘)[0].contents[1].text) day=(news.select(‘.news-list-info‘)[0].contents[0].text) url=news.select(‘a‘)[0][‘href‘] title=(news.select(‘.news-list-title‘)[0].text) resd=requests.get(url) resd.encoding=‘utf-8‘ soupd=BeautifulSoup(resd.text,"html.parser") textd=(soupd.select(‘.show-content‘)[0].text) date=getdate(url) print(day,title,sorce,date) gzccurl=‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘ res=requests.get(gzccurl) res.encoding=‘utf-8‘ soup=BeautifulSoup(res.text,"html.parser") n=int(soup.select(‘.a1‘)[0].text.rstrip(‘条‘)) page=n//10+1 for i in range(1,7): pageurl=‘http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html‘.format(i) print(pageurl)
标签:标题 groups none arc img gen day blog 工作
原文地址:http://www.cnblogs.com/a939833950/p/7655369.html