爬取所有校园新闻
1.获取单条新闻的#标题#链接#时间#来源#内容 #点击次数,并包装成一个函数。
import requests from bs4 import BeautifulSoup network = 'http://news.gzcc.cn/html/xiaoyuanxinwen/' res = requests.get(network) res.encoding='utf-8' soup = BeautifulSoup(res.text,'html.parser') 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 main = news.select('.news-list-description')[0].text source = news.select('.news-list-info')[0].contents[1].text print('链接:{}'.format(url)) print('标题:{}'.format(title)) print('正文:{}'.format(main)) print('时间:{}'.format(time)) print('来源:{}'.format(source)) res1 = requests.get(url) res1.encoding='utf-8' soup1 = BeautifulSoup(res1.text,'html.parser') passage = soup1.select('.show-content') click = int(requests.get('http://oa.gzcc.cn/api.php?op=count&id=8307&modelid=80').text.split('.')[-1].lstrip("html('").rstrip("');")) print('点击次数:{}'.format(click)) break
2.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。
import requests from bs4 import BeautifulSoup from datetime import datetime import re network = 'http://news.gzcc.cn/html/xiaoyuanxinwen/' res = requests.get(network) res.encoding='utf-8' soup = BeautifulSoup(res.text,'html.parser') 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=8307&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: title = news.select('.news-list-title')[0].text url = news.select('a')[0]['href'] time = news.select('.news-list-info')[0].contents[0].text timed = datetime.strptime(time,'%Y-%m-%d') main = news.select('.news-list-description')[0].text source = news.select('.news-list-info')[0].contents[1].text print('链接:{}'.format(url)) print('标题:{}'.format(title)) print('正文:{}'.format(main)) print('时间:{}'.format(timed)) print('来源:{}'.format(source)) res1 = requests.get(url) res1.encoding='utf-8' soup1 = BeautifulSoup(res1.text,'html.parser') passage = soup1.select('.show-content') click = getclick(url) print('点击次数:{}'.format(click))
3.获取所有新闻列表页的网址,调用上述函数。
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') 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 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') text_list = soup_list.select('.show-content')[0].text hits_list = gethits(href) getpageinfo(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_page.text,'html.parser') list_page = soup.select('li') getpageinfo(list_page) print(url_page)
4.完后所有校园新闻爬取工作
import requests from bs4 import BeautifulSoup from datetime import datetime 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=8307&modelid=80'.format(id) click = int(requests.get(clickurl).text.split('.')[-1].lstrip("html('").rstrip("');")) return(click) def getonepage(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: title = news.select('.news-list-title')[0].text url = news.select('a')[0]['href'] time = news.select('.news-list-info')[0].contents[0].text timed = datetime.strptime(time,'%Y-%m-%d') main = news.select('.news-list-description')[0].text source = news.select('.news-list-info')[0].contents[1].text print('链接:{}'.format(url)) print('标题:{}'.format(title)) print('正文:{}'.format(main)) print('时间:{}'.format(timed)) print('来源:{}'.format(source)) res1 = requests.get(url) res1.encoding='utf-8' soup1 = BeautifulSoup(res1.text,'html.parser') click = getclick(url) print('点击次数:{}'.format(click)) getonepage('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') page = int(soup.select('.a1')[0].text.rstrip('条'))//10+1 for i in range(2,page+1): listurl='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i) getonepage(listurl)