15 案例_单一版面列表抓取

版权声明：转载请注明出处 https://blog.csdn.net/nanhuaibeian/article/details/86613676

1.借助Postman生成Headers

​如果Headers中如果 含有if-modified-since也需要拿掉。

2.分析网页

3.代码

import requests
import re
from lxml import etree

class BoardListCrawler:
    headers = {
        'Accept': "*/*",
        'Accept-Encoding': "gzip, deflate",
        'Accept-Language': "zh-CN,zh;q=0.9",
        'Connection': "keep-alive",
        'Host': "www.newsmth.net",
        'Referer': "http://www.newsmth.net/nForum/",
        'User-Agent': "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.80 Safari/537.36",
        'X-Requested-With': "XMLHttpRequest",
        'cache-control': "no-cache",
    }

    domain = "https://www.newsmth.net"
    base_url = domain + "/nForum/section/{}?ajax"

    def get_content(self,page_number):
        #[format函数参考](https://blog.csdn.net/nanhuaibeian/article/details/86591202)
        url = self.base_url.format(page_number)
        response = requests.get(url,headers= self.headers)
        return response.text

    def get_board_list(self,content):
        boards = []
        tree = etree.HTML(content)
        rows = tree.xpath("//table[@class='board-list corner']/tbody/tr")
        for row in rows:
            board = {}
            columns = row.xpath('td')
            board['url'] = columns[0].xpath('a')[0].attrib['href']
            board['title'] = columns[0].xpath('a')[0].text
            #主题数量
            board['num_topics'] = columns[5].text
            #文章数量
            board['num_posts'] = columns[6].text
            boards.append(board)
            print(board)

if __name__ =='__main__':
    blc = BoardListCrawler()
    c = blc.get_content(1)
    blc.get_board_list(c)

4.结果

​