Python学习爬虫 requests库

Posted 2021-03-11 gisoracle

下载图片
import requests

response = requests.get(‘http://www.51gis.com.cn/static/upload/3e223daf9df6216f/f3e187dfc0e4143a.jpg‘)

with open(‘51gis.jpg‘, ‘wb‘) as f:
    f.write(response.content)

 ==================================

import requests


class TiebaSpider(object):
    def __init__(self, tieba_name):
        self.tieba_name = tieba_name
        self.url_temp = "http://tieba.baidu.com/f?kw=" + tieba_name + "&ie=utf-8&pn={}"
        self.headers = {
            ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.75 Safari/537.36‘
        }

    def parse_url(self, url):
        #‘‘‘访问url‘‘‘
        response = requests.get(url, headers=self.headers)
        return response.text

    def save_html(self, url_html, page_num):
        ‘‘‘保存页面‘‘‘
        file_path = "《{}》-第{}页".format(self.tieba_name, page_num)
        with open(file_path + ‘.htm‘, ‘w‘) as f:
            f.write(url_html)

    def get_url_list(self):
        ‘‘‘构造url列表‘‘‘
        # 方法1
        url_list = []
        for i in range(10):
            url_list.append(self.url_temp.format(i * 50))

        return url_list

        # 方法2
        #return [self.url_temp.format(i * 50) for i in range(10)]


    def run(self):
        ‘‘‘主要逻辑‘‘‘
        # 1 构造url
        url_list = self.get_url_list()
        # 2 访问url
        for url in url_list:
            url_html = self.parse_url(url)
            # 3 保存
            page_num = url_list.index(url) + 1  # 获取页码
            self.save_html(url_html, page_num)


if __name__ == ‘__main__‘:
    name = input(‘请输入你想要爬取的论坛名称：‘)
    tb_spider = TiebaSpider(name)
    tb_spider.run()