Python糗事百科爬虫

糗事百科爬虫

-通过面向对象实现糗事百科页面爬取

• 使用xpath解析页面

import requests
from lxml import etree 

class Qiubai:
    def __init__(self):
        self.temp_url = "https://www.qiushibaike.com/hot/page/{}"
        self.headers = {"user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.68 Safari/537.36"}
    
    def get_url_list(self):
        return [self.temp_url.format(i) for i in range(1,14)]
    
    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)
        div_list = html.xpath("//div[@class='col1 old-style-col1']/div")
        content_list = []
        for div in div_list:
            item = {}
            item['user_name'] = div.xpath(".//h2/text()")[0].strip()
            item['content'] = [i.strip() for i in div.xpath(".//div[@class='content']/span/text()")]
            content_list.append(item)
        return content_list
    def save_content_list(self,content_list):
        for content in content_list:
            print(content)


    def run(self):
        #1. 准备url列表
        url_list = self.get_url_list()
        #2. 遍历发送请求，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.保存数据
            self.save_content_list(content_list)

if __name__ == "__main__":
    qiubai = Qiubai()
    qiubai.run()

本文地址：https://blog.csdn.net/qq_44224678/article/details/107154891