糗事百科爬虫案例

Posted 2022-09-01 -chenxs

爬取糗事百科的热门的所有段子的作者、标题、内容链接、好笑数、评论数

# coding=utf-8

from lxml import etree
import requests
import json
class QiubaiSpider:
    def __init__(self):
        self.url_temp="https://www.qiushibaike.com/8hr/page//"
        self.header="User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/76.0.3809.100 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):
        print("正在爬取：",url)
        response=requests.get(url,headers=self.header)
        return response.content.decode()
    def get_content_list(self,html_str):
        html=etree.HTML(html_str)
        #1.分组
        div_list=html.xpath("//div[@class=‘recommend-article‘]//li")
        content_list=[]
        for div in div_list:
            item=
            item["作者名"]=div.xpath(".//span[@class=‘recmd-name‘]/text()")[0] if len(div.xpath(".//span[@class=‘recmd-name‘]/text()"))>0 else None
            item["标题"]=div.xpath(".//a[@class=‘recmd-content‘]/text()")
            item["内容链接"]=div.xpath(".//a[@class=‘recmd-content‘]/@href")
            item["内容链接"]=‘https://www.qiushibaike.com‘+item["内容链接"][0] if len(item["内容链接"])>0 else None
            item["好笑数"]=div.xpath(".//div[@class=‘recmd-num‘]/span/text()")
            item["好笑数"]=item["好笑数"][0] if len(item["好笑数"])>0 else None
            item["评论"]=div.xpath(".//div[@class=‘recmd-num‘]/span/text()")[-2]
            #item["评论"]=item["评论"][3] if len(item["评论"])>0 else None
            content_list.append(item)
        return content_list
    #b保存
    def save_content(self,content_list):
        with open("qiubai.txt","a",encoding="utf-8") as f:
            for content in content_list:
                f.write(json.dumps(content,ensure_ascii=False))
                f.write("\n")
        print("保存成功")

    def run(self):
        #1.根据url地址规律，构造url列表
        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)
            #3.提取数据
            content_list=self.get_content_list(html_str)
            #4.保存
            self.save_content(content_list)

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