requests爬取糗事百科页面

requests爬取糗事百科,由于糗事百科是静态页面,用简单的requests即可代码如下:

import requests
import lxml.html


class Qiu:
    def __init__(self, name_, url_base):
        """
        设置基础参数
        :param addr:
        """
        self.name_ = name_
        self.url_base = url_base + "/{}/"
        # 设置headers
        self.headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36"
        }

    def make_url_lists(self):
        """
        生成下载的url地址列表
        :return:
        """
        url_lists = [self.url_base.format(i) for i in range(2)]
        return url_lists

    def download_url(self, down_url):
        """
        下载指定页面
        :return: 下载到的html页面内容
        """
        result = requests.get(down_url, headers=self.headers)
        print(result.text)
        return result.content

    def save_result(self, result, page_num):
        file_path = "qiushi/{}第{}页.html".format(self.name_, page_num)
        with open(file_path, "wb") as f:
            f.write(result)


    def run(self):
        # 获取url下载页面列表
        url_lists = self.make_url_lists()
        # 遍历这个列表
        for url_list in url_lists:
            # 调用download_url函数获取每个url页面的content
            result = self.download_url(url_list)
            # 获取这个页面是所有下载列表中的第几个
            pg_num = url_lists.index(url_list) + 1
            # 调用save_result函数保存这个html页面
            self.save_result(result, pg_num)
            # 对html页面内容解码为字符串格式
            result = result.decode('utf-8')
            #
            url_content = lxml.html.fromstring(result)
            html_data = url_content.xpath("//div[@class='content']/span")
            txt = 'text/糗事百科第{}页.txt'.format(pg_num)
            with open(txt, 'wb') as f:
                for i in html_data:
                    f.write(i.text.encode('utf-8'))


if __name__ == "__main__":
    qiu = Qiu("糗事百科", "https://www.qiushibaike.com/8hr/page")
    qiu.run()
    # qiu.result_content()