1 import requests
 2 import json
 3 import re
 4
 5 comments_url = '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'
 6
 7 def getCommentsCount(newsURL):
 8     ID = re.search('doc-i(.+).shtml', newsURL)
 9     newsID = ID.group(1)
10     commentsURL = requests.get(comments_url.format(newsID))
11     commentsTotal = json.loads(commentsURL.text.strip('var data='))
12     return commentsTotal['result']['count']['total']
13
14 news = 'http://news.sina.com.cn/c/nd/2017-05-14/doc-ifyfeius7904403.shtml'
15 print(getCommentsCount(news))

 1 from bs4 import BeautifulSoup
 2 import requests
 3 from datetime import datetime
 4 import json
 5 import re
 6
 7 comments_url = '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'
 8
 9 def getCommentsCount(newsURL):
10     ID = re.search('doc-i(.+).shtml', newsURL)
11     newsID = ID.group(1)
12     commentsURL = requests.get(comments_url.format(newsID))
13     commentsTotal = json.loads(commentsURL.text.strip('var data='))
14     return commentsTotal['result']['count']['total']
15
16 # news = 'http://news.sina.com.cn/c/nd/2017-05-14/doc-ifyfeius7904403.shtml'
17 # print(getCommentsCount(news))
18
19 def getNewsDetail(news_url):
20     result = {}
21     web_data = requests.get(news_url)
22     web_data.encoding = 'utf-8'
23     soup = BeautifulSoup(web_data.text,'lxml')
24     result['title'] = soup.select('#artibodyTitle')[0].text
25     result['comments'] = getCommentsCount(news_url)
26     time = soup.select('.time-source')[0].contents[0].strip()
27     result['dt'] = datetime.strptime(time,'%Y年%m月%d日%H:%M')
28     result['source'] = soup.select('.time-source span span a')[0].text
29     result['article'] = ' '.join([p.text.strip() for p in soup.select('#artibody p')[:-1]])
30     result['editor'] = soup.select('.article-editor')[0].text.lstrip('责任编辑：')
31     return result
32
33 print(getNewsDetail('http://news.sina.com.cn/c/nd/2017-05-14/doc-ifyfeius7904403.shtml'))