爬虫糗事百科实例

糗事百科实例：

爬取糗事百科段子，假设页面的URL是 http://www.qiushibaike.com/8hr/page/1

要求：

1. 使用requests获取页面信息，用XPath / re 做数据提取
2. 获取每个帖子里的用户头像链接、用户姓名、段子内容、点赞次数和评论次数
3. 保存到 json 文件内

参考代码

import json
import requests
from lxml import etree

page = 1
url = 'http://www.qiushibaike.com/8hr/page/' + 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'}


def get_page():
    response = requests.get(url, headers=headers)
    # response.encoding = response.apparent_encoding
    if response.status_code == 200:
        return response.text
    else:
        return None


def parse():
    resHtml = get_page()
    if resHtml is None:
        return
    html = etree.HTML(resHtml)
    result = html.xpath('//div[contains(@id,"qiushi_tag")]')
    items = []
    for site in result:
        try:
            item = {}

            imgurl = site.xpath('./div/a/img/@src')[0]
            # username = site.xpath('./div/a/@title')[0]
            username = site.xpath('.//h2')[0].text
            content = site.xpath('.//div[@class="content"]/span')[0].text.strip()
            # 投票次数
            vote = site.xpath('.//i')[0].text
            # print site.xpath('.//*[@class="number"]')[0].text
            # 评论信息
            comments = site.xpath('.//i')[1].text

            item['imgurl'] = imgurl
            item['username'] = username
            item['content'] = content
            item['vote'] = vote
            item['comments'] = comments
            print(imgurl, username, content, vote, comments)
            items.append(item)
        except Exception as e:
            print(e)
    return items


def save_items(items):
    with open('qiushibaike.json', 'w', encoding='utf-8') as f:
        f.write(json.dumps(items))


def main():
    items = parse()
    save_items(items)


if __name__ == '__main__':
    main()