项目练习 —— 贴吧爬虫

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

import requests

class TiebaSpider(object):
    def __init__(self, tieba_name):
        self.tieba_name = tieba_name
        self.url_temp = "https://tieba.baidu.com/f?kw=" + tieba_name + "&ie=utf-8&pn={}"
        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 get_url_list(self):
        """构造URL列表"""
        # url_list = []
        # for i in range(10):
        #     url_list.append(self.url_temp.format(i * 50))
        # return url_list
        return [self.url_temp.format(i * 50) for i in range(10)]

    def parse_url(self, url):
        """遍历列表，发送请求，获取响应内容"""
        # print(url)
        respond = requests.get(url, headers = self.headers)
        return respond.content.decode()


    def save_html(self, html_str, page_number):
        """保存数据"""
        file_name = "{} 第{}页" .format(self.tieba_name, page_number)
        with open(file_name, "w", encoding="utf-8") as f:
            f.write(html_str)

    def run(self):

        # 构造URL列表
        url_list = self.get_url_list()
        print(url_list)
        # 遍历列表，发送请求，获取响应内容
        for url in url_list:
            html_str = self.parse_url(url)
            # 保存数据
            page_number = url_list.index(url) + 1
            self.save_html(html_str, page_number)


if __name__ == "__main__":
    tieba_sipder = TiebaSpider("棋魂")
    tieba_sipder.run()