糗百热点爬虫

# -*- coding:utf-8 -*-
# Author:Sure Feng

import requests
from lxml import etree
import json


class QiubaiSpider(object):
    def __init__(self):
        self.tempt_url = "https://www.qiushibaike.com/8hr/page/{}/"
        self.headers = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36"}

    def parse_url(self, url):
        """发送请求，获取响应"""
        respond = requests.get(url, self.headers)
        return respond.content.decode()

    def get_content(self, html_str, num):
        """提取数据"""
        html = etree.HTML(html_str)
        div_list = html.xpath("//div[@id='content-left']/div")  # 分组
        content_list = []
        for div in div_list:
            item = {}
            item["page"] = num
            item["content"] = div.xpath(".//div[@class='content']/span/text()")
            item["content"] = [i.replace("
","") for i in item["content"]]
            item["author_gender"] = div.xpath(".//div[contains(@class, 'articleGender')]/@class")
            item["author_gender"] = item["author_gender"][0].split(" ")[-1].replace("Icon", "") if len(item["author_gender"])>0 else None
            item["age"] = div.xpath(".//div[contains(@class, 'articleGender')]/text()")
            item["age"] = item["age"][0] if len(item["age"])>0 else None
            item["content_img"] = div.xpath(".//div[@class='thumb']/a/img/@src")
            item["content_img"] = "https" + item["content_img"][0] if len(item["content_img"])>0 else None
            item["author_img"] = div.xpath(".//div[@class='author clearfix']//img/@src")
            item["author_img"] = "https:" + item["author_img"][0] if len(item["author_img"])>0 else None
            item["stats_vote"] = div.xpath(".//span[@class='stats-vote']/i/text()")
            item["stats_vote"] = item["stats_vote"][0] if len(item["stats_vote"])>0 else None
            content_list.append(item)
        return content_list

    def save_conten(self, content_list):
        """保存"""
        with open("qiubai.txt", "a", encoding="utf-8") as f:
            for content in content_list:
                f.write(json.dumps(content, ensure_ascii=False, indent=4))
                f.write("
")
        print("保存成功")

    def run(self):  # 实现主要逻辑
        # 获取URL列表，遍历列表
        start_url = [self.tempt_url.format(i) for i in range(1, 14)]
        num = 1
        for url in start_url:
            # 发送请求，获取响应
            html_str = self.parse_url(url)
            # 提取数据
            content_list = self.get_content(html_str, num)
            # 保存
            self.save_conten(content_list)
            num += 1


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