Python_网络爬虫（新浪新闻抓取）

1 soup = BeautifulSoup(res.text,‘html.parser‘)
2 # 将requests获取的网页信息转换为BeautifulSoup的物件存于soup中，并指明其剖析器为‘html.parser‘，否则会出现警告。

1 alink = soup.select(‘h1‘)
2 
3 for link in alink:
4     print(link.text)

1 for link in soup.select(‘a‘):
2   　print(link[‘href‘])

1 import re
2 
3 m = re.search（‘ doc-i(.*).shtml ‘,newsurl）　　# 返回在newsurl中匹配到的字符串
4 print(m.group(1))　　# group（0）可以取得所有匹配到的部分，group（1）只可以取得括号内的部分

1 url = ‘http://api.roll.news.sina.com.cn/zt_list?channel=news&cat_1=gnxw&cat_2==gdxw1||=gatxw||=zs-pl||=mtjj&level==1||=2&show_ext=1&show_all=1&show_num=22&tag=1&format=json&page={}&callback=newsloadercallback&_=1501000415111‘
2  
3 for i in rannge（0,10）：
4 　　print( url.format( i ) )
5 # format可以将url里面的大括号（要修改的部分我们把它删去并换成大括号）换为我们要加入的值（如上面代码中的 i）

1 # 获取出版时间
2 from datetime import datetime
3 
4 res = requests.get(‘http://news.sina.com.cn/c/nd/2017-07-22/doc-ifyihrmf3191202.shtml‘)
5 res.encoding = ‘utf-8‘
6 soup = BeautifulSoup(res.text,‘html.parser‘)
7 timesource = soup.select(‘.time-source‘)
8 print(timesource[0].contents[0]) 

1 # 字符串转时间：-strptime
2 dt = datetime.strptime(timesource,‘%Y年%m月%d日%H：%M ’）
3 
4 # 时间转换字符串：-strftime
5 dt.strftime(‘%Y-%m-%d‘）

1 # 获取单篇新闻内容
2 article = []
3 for p in soup.select(‘.article p‘):
4     article.append(p.text.strip())
5 print(‘\n‘.join(article))

1 # 一行完成上面获取新闻内容的代码
2 print(‘\n‘.join([p.text.strip() for p in soup.select(‘.article p‘)]))

1 # 取得评论数的数量
2 import requests
3 import json
4 comment = requests.get(‘http://comment5.news.sina.com.cn/page/info?version=1&format=js&c5 hannel=gn&newsid=comos-fyihrmf3218511&group=&compress=0&ie=utf-8&oe=utf-8&page=1&page_size=20‘)　　# 从评论地址获取相关内容
6 comment.encoding = ‘utf-8‘
7 jd = json.loads(comment.text.strip(‘var data=‘))
8 jd[‘result‘][‘count‘][‘total‘]

 1 # 获取新闻的标题，内容，时间和评论数
 2 import requests
 3 from bs4 import BeautifulSoup
 4 from datetime import datetime
 5 import re
 6 import json
 7 import pandas
 8 
 9 def getNewsdetial(newsurl):
10     res = requests.get(newsurl)
11     res.encoding = ‘utf-8‘
12     soup = BeautifulSoup(res.text,‘html.parser‘)
13     newsTitle = soup.select(‘.page-header h1‘)[0].text.strip()
14     nt = datetime.strptime(soup.select(‘.time-source‘)[0].contents[0].strip(),‘%Y年%m月%d日%H:%M‘)
15     newsTime = datetime.strftime(nt,‘%Y-%m-%d %H:%M‘)
16     newsArticle = getnewsArticle(soup.select(‘.article p‘))
17     newsAuthor = newsArticle[-1]
18     return newsTitle,newsTime,newsArticle,newsAuthor
19 def getnewsArticle(news):
20     newsArticle = []
21     for p in news:
22          newsArticle.append(p.text.strip())
23     return newsArticle
24 
25 # 获取评论数量
26 
27 def getCommentCount(newsurl):
28     m = re.search(‘doc-i(.+).shtml‘,newsurl)
29     newsid = m.group(1)
30     commenturl = ‘http://comment5.news.sina.com.cn/page/info?version=1&format=js&channel=gn&newsid=comos-{}&group=&compress=0&ie=utf-8&oe=utf-8&page=1&page_size=20‘
31     comment = requests.get(commenturl.format(newsid))   #将要修改的地方换成大括号，并用format将newsid放入大括号的位置
32     jd = json.loads(comment.text.lstrip(‘var data=‘))
33     return jd[‘result‘][‘count‘][‘total‘]
34 
35 
36 def getNewsLinkUrl():
37 #     得到异步载入的新闻地址（即获得所有分页新闻地址）
38     urlFormat = ‘http://api.roll.news.sina.com.cn/zt_list?channel=news&cat_1=gnxw&cat_2==gdxw1||=gatxw||=zs-pl||=mtjj&level==1||=2&show_ext=1&show_all=1&show_num=22&tag=1&format=json&page={}&callback=newsloadercallback&_=1501000415111‘
39     url = []
40     for i in range(1,10):
41         res = requests.get(urlFormat.format(i))
42         jd = json.loads(res.text.lstrip(‘  newsloadercallback(‘).rstrip(‘);‘))
43         url.extend(getUrl(jd))     #entend和append的区别
44     return url
45 
46 def getUrl(jd):
47 #     获取每一分页的新闻地址
48     url = []
49     for i in jd[‘result‘][‘data‘]:
50         url.append(i[‘url‘])
51     return url
52 
53 # 取得新闻时间，编辑，内容，标题，评论数量并整合在total_2中
54 def getNewsDetial():
55     title_all = []
56     author_all = []
57     commentCount_all = []
58     article_all = []
59     time_all = []
60     url_all = getNewsLinkUrl()
61     for url in url_all:
62         title_all.append(getNewsdetial(url)[0])
63         time_all.append(getNewsdetial(url)[1])
64         article_all.append(getNewsdetial(url)[2])
65         author_all.append(getNewsdetial(url)[3])
66         commentCount_all.append(getCommentCount(url))
67     total_2 = {‘a_title‘:title_all,‘b_article‘:article_all,‘c_commentCount‘:commentCount_all,‘d_time‘:time_all,‘e_editor‘:author_all}
68     return total_2
69 
70 # ( 运行起始点 )用pandas模块处理数据并转化为excel文档
71 
72 df = pandas.DataFrame(getNewsDetial())
73 df.to_excel(‘news2.xlsx‘)