糗事百科爬虫(一)

"""
@author:Rudy

@time : 12月4日

@message:爬取糗事百科热门上的段子用户昵称

"""

"""
注意事项:
1 知道url的规律,知道一共多少页,准备url列表,比如豆瓣电影
2 不知道url的规律,或者不知道一共多少页,准备satrt_url,比如贴吧

"""

import requests
from lxml import etree


class QiuBai():
    def __init__(self):
        self.temp_url = "https://www.qiushibaike.com/8hr/page{}"
        self.headers = {
            "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 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):  # 提取数据
        html = etree.HTML(html_str)
        div_list = html.xpath("//div[@id='content-left']/div")
        content_list = []
        for div in div_list:
            item = {}
            item["user_name"] = div.xpath(".//h2/text()")
            item["content"] = [i.strip() for i in div.xpath(".//div[@class='content']/span/text()")] # 列表推导式
            content_list.append(item)
        return content_list

    def save_content_list(self, content_list):
        for content in content_list:
            print(content)

    def run(self):  # 实现主要的逻辑
        # 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
            self.save_content_list(content_list)


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