获取全部校园新闻

 1 import requests
 2 from bs4 import BeautifulSoup
 3 from datetime import datetime
 4 import re
 5 # res = requests.get(‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘)
 6 # res.encoding = ‘utf-8‘
 7 # soup = BeautifulSoup(res.text, ‘html.parser‘)
 8 
 9 
10 # 获取新闻点击次数
11 def getNewsId(url):
12     #使用正则表达式获得新闻编号
13     newsId = re.findall(r‘\_(.*).html‘, url)[0][-4:]
14     #生成点击次数的Request URL
15     clickUrl = ‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(newsId)
16     clickRes = requests.get(clickUrl)
17     # 利用正则表达式获取新闻点击次数
18     clickCount = int(re.search("hits‘\).html\(‘(.*)‘\);", clickRes.text).group(1))
19     return clickCount
20 
21 
22 
23 def getNewDetail(newsurl):
24     # 读取新闻详情
25     resDescript = requests.get(newsurl)
26     resDescript.encoding = "utf-8"
27     soupDescript = BeautifulSoup(resDescript.text, ‘html.parser‘)
28     title = soupDescript.select(‘.show-title‘)[0].text
29     info = soupDescript.select(‘.show-info‘)[0].text
30     if (info.find(‘作者‘) > 0):
31         author = re.search(‘作者：((.{2,20}\s|.{2,20}、|.{2,20}，){1,5})‘, info).group(1)
32     else:
33         author = ‘none‘
34     if (info.find(‘审核‘) > 0):
35         right = re.search(‘审核：((.{2,20}\s|.{2,20}、|.{2,20}，){1,5})‘, info).group(1)
36     else:
37         right = ‘none‘
38     if (info.find(‘来源‘) > 0):
39         source = re.search(‘来源：((.{2,50}\s|.{2,50}、|.{2,50}，){1,5})‘, info).group(1)
40     else:
41         source = ‘none‘
42     if (info.find(‘摄影‘) > 0):
43         video = re.search(‘摄影：((.{2,50}\s|.{2,50}、|.{2,50}，){1,5})‘, info).group(1)
44     else:
45         video = ‘none‘
46     # author = re.search(‘作者：((.{2,20}\s|.{2,20}、|.{2,20}，){1,5})‘, info).group(1)
47     # right = re.search(‘审核：(.*)\xa0\xa0来源：‘, info).group(1)
48     # source = re.search(‘来源：(.*)\xa0\xa0\xa0\xa0摄影：‘, info).group(1)
49     # video = re.search(‘摄影：(.*)\xa0\xa0\xa0\xa0点击：‘, info).group(1)
50     dt = datetime.strptime(info.lstrip(‘发布时间:‘)[0:19],‘%Y-%m-%d %H:%M:%S‘)
51     content = soupDescript.select(‘.show-content‘)[0].text.strip()
52     click = getNewsId(newsurl)
53     # print(click,title,newsurl,source,dt)
54     print(‘发布时间：{0}\n作者：{1}\n审核：{2}\n来源：{3}\n摄影：{4}\n点击次数：{5}‘.format(dt, author, right, source, video, click))
55 
56 def getListPage(listPageUrl):
57     res1 = requests.get(listPageUrl)
58     res1.encoding = ‘utf-8‘
59     soup = BeautifulSoup(res1.text,‘html.parser‘)
60     for news in soup.select(‘li‘):
61         if len(news.select(‘.news-list-title‘))>0:
62             a = news.select(‘a‘)[0].attrs[‘href‘]
63             getNewDetail(a)
64 
65 resn = requests.get(‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘)
66 resn.encoding = ‘utf-8‘
67 soupn = BeautifulSoup(resn.text,‘html.parser‘)
68 #新闻总篇数
69 listcount = int(soupn.select(‘.a1‘)[0].text.rstrip(‘条‘))
70 print(listcount)
71 #新闻总页数
72 n = int(soupn.select(‘.a1‘)[0].text.rstrip(‘条‘))//10+1
73 
74 #首页
75 # getListPage(‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘)
76 
77 #最后一页
78 for i in range(n,n+1):
79     pageUrl = ‘http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html‘.format(i)
80     getListPage(pageUrl)