小爬新浪新闻AFCCL

#!/usr/bin/env/python
# coding:utf-8
import sys
import requests
from bs4 import BeautifulSoup
import json
import re
if __name__ == ‘__main__‘:
	url = ‘http://sports.sina.com.cn/z/AFCCL/‘
	res = requests.get(url)
	html_doc = res.content

	soup = BeautifulSoup(html_doc, ‘html.parser‘)

	a_list=[]
	#爬取新闻时间，标题，链接
	for news in  soup.select(‘.news-item‘):
		if(len(news.select(‘h2‘))>0):
			h2=news.select(‘h2‘)[0].text
			a=news.select(‘a‘)[0][‘href‘]
			time=news.select(‘.time‘)[0].text
			# print(time,h2,a)
			a_list.append(a)
	#爬取内文资料
	for i in range(len(a_list)):
		url=a_list[i]
		res = requests.get(url)
		html_doc = res.content
		soup = BeautifulSoup(html_doc, ‘html.parser‘)
		#获取文章标题、时间、来源、内容,评论数
		title=soup.select(‘#j_title‘)
		if title:
			title = soup.select(‘#j_title‘)[0].text.strip()
			time = soup.select(‘.article-a__time‘)[0].text.strip()
			source = soup.select(‘.article-a__source‘)[0].text.strip()
			content = soup.select(‘.article-a__content‘)[0].text.strip()
			#动态生成获取评论的Ajax url eg:‘http://comment5.news.sina.com.cn/page/info?version=1&format=js&channel=ty&newsid=comos-fykiuaz1429964&group=&compress=0&ie=utf-8&oe=utf-8&page=1&page_size=20&jsvar=loader_1504416797470_64712661‘
			# print(url)
			pattern_id=r‘(fyk\w*).s?html‘
			# print(re.search(pattern_id,url).group(1))
			id=re.search(pattern_id,url).group(1)
			url=‘http://comment5.news.sina.com.cn/page/info?version=1&format=js&channel=ty&newsid=comos-‘+id+‘&group=&compress=0&ie=utf-8&oe=utf-8&page=1&page_size=20‘
			comments = requests.get(url)
			jd=json.loads(comments.text.strip(‘var data=‘))
			commentCount = jd[‘result‘][‘count‘][‘total‘] # 评论数
			print(time,title,source,content)
			print(commentCount)