爬取贴吧图片

import requests
from lxml import etree


class TieBa(object):
    def __init__(self):
        self.url = 'https://tieba.baidu.com/kw=%E7%BE%8E%E5%A5%B3'
        self.headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko"}

    def send_response(self, url, params={} ):
        response = requests.get(url, headers=self.headers, params=params)
        data = response.content
        return data

    def write_file(self, data, image_name):
        print(image_name)
        image_path = 'images/' + image_name
        with open(image_path, 'wb') as f:
            f.write(data)

    def parse_data(self, data, rule):
        html_data = etree.HTML(data)
        result_list = html_data.xpath(rule)
        # print(result_list)
        return result_list

    def run(self):
        params = {
            "kw": "美女",
            "pn": 0
        }
        data = self.send_response(self.url, params)
        rule = '//div[@class="t_con cleafix"]/div/div/div/a/@href'
        utl_list = self.parse_data(data, rule)
        for detail in utl_list:
        	# 拼接url
            detail_url = 'https://tieba.baidu.com' + detail
            data = self.send_response(detail_url)
            # 2.1 解析所有的图片的 url
            image_rule = '//img[@class="BDE_Image"]/@src'
            image_url_list = self.parse_data(data, image_rule)

            # 3.发送图片的请求
            for img_url in image_url_list:
                img_data = self.send_response(img_url)
                # 图片的名字
                image_name = img_url[-15:]
                # 保存图片
                self.write_file(img_data, image_name)

        # self.write_file(data)


if __name__ == '__main__':
    TieBa().run()