糗事百科_爬虫_案例

import requests
from lxml import etree
import json

class QiubaiSpider:
    def __init__(self):
        self.url_temp="https://www.qiushibaike.com/8hr/page/{}/"
        self.headers = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36"}

    def get_url_list(self):
        url_list=[self.url_temp.format(i) for i in range(1,14)]
        return url_list

    def parse_url(self,url):
        response = requests.get(url, headers= self.headers)
        return response.content.decode()

    def get_content_list(self,html_str):
        html = etree.HTML(html_str)
        #1. 分组
        div_list = html.xpath("//div[@id='content-left']/div")
        content_list = []

        for div in div_list :
            item = {}
            item['author_name']=div.xpath(".//h2//text()")[0].strip() if len(div.xpath(".//h2//text()"))>0 else None
       
            item["content"] = div.xpath(".//div[@class='content']/span/text()")
            item['content']=[i.strip() for i in item['content']]
            item['status_vote'] = div.xpath("//span[@class='stats-vote']/i/text()")
            item['status_vote'] = item['status_vote'][0] if len(item['status_vote'])>0 else None
            content_list.append(item)

        return content_list

    def save_content_list(self,content_list):
        with open("qibai.txt",'a',encoding='utf-8') as f:
            for content in content_list:
                f.write(json.dumps(content,ensure_ascii=False))
                f.write("\n")
        print ("save successfully")

    def run(self):
        #1.根据url地址的规律，构造url list
        url_list = self.get_url_list()
        #2. 发送请求，获取响应
        for url in url_list:
            html_str = self.parse_url(url)
            content_list=self.get_content_list(html_str) #3.提取数据
            self.save_content_list(content_list) #4.保存

if __name__ == '__main__':
    qiubai= QiubaiSpider()
    qiubai.run()