NO.33——XPath选择器爬取糗事百科段子

       对应接口是https://www.qiushibaike.com。这个爬虫比较简单，简单分析下网页构成：

代码实战：

# -*- coding:utf-8 -*-
import urllib
import requests
import re
import chardet
from lxml import etree

page = 2
url = 'http://www.qiushibaike.com/8hr' + str(page) + "/"
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36',
    'Accept-Language': 'zh-CN,zh;q=0.8'}
try:
    response = requests.get(url, headers=headers)
    resHtml = response.text
    #解析网页源码
    html = etree.HTML(resHtml)
    result = html.xpath('//div[contains(@id,"qiushi_tag")]')
    for site in result:
        
        item = {}
        #[0]是头像，[1]是内容图片
        imgUrl = site.xpath('./div/a/img/@src')[0].encode('utf-8')
        username = site.xpath('.//h2')[0].text
        content = site.xpath('.//div[@class="content"]')[0].text.strip().encode('utf-8')
        vote = site.xpath('.//i')[0].text
        comments = site.xpath('.//i')[1].text

        print imgUrl, username, content, vote, comments

except Exception as e:
    print e