linux中vim编辑器的应用实例

针对数据提取的项目实战：

# -*- coding: utf-8 -*-
from lxml import etree

text = '''
<div>  
    <ul>  
        <li class="item-1">
            <a href="link1.html">first item</a>
        </li>  
        <li class="item-1">
            <a href="link2.html">second item</a>
        </li>  
        <li class="item-inactive">
            <a href="link3.html">third item</a>
        </li>  
        <li class="item-1">
            <a href="link4.html">fourth item</a>
        </li>  
        <li class="item-0">
            <a href="link5.html">fifth item</a>
        </li>  
    </ul>  
</div>
'''

html = etree.HTML(text)
print(etree.tostring(html))

运行结果，可以看出body等标签自动已补全。

 实现对百度贴吧爬取：

注意点1： 

这里提供一些老版本的User-Agent ：

注意点2： 

 注意点3：

# -*- coding: utf-8 -*-
import requests
from lxml import etree


# url
# headers
# 发送请求获取响应
# 从响应中提取数据
# 判断结束
class Tieba(object):
    def __init__(self, name):
        self.url = "https://tieba.baidu.com/f?kw={}".format(name)
        print(self.url)
        self.headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36"
            # "User-Agent": "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; T132461)"

        }

    def get_data(self, url):
        response = requests.get(url, headers=self.headers)
        with open("temp.html", "wb") as f:
            f.write(response.content)
        return response.content

    def parse_data(self, data):
        # 创建element对象
        data = data.decode().replace("<!--", "").replace("-->", "")
        html = etree.HTML(data)
        el_list = html.xpath('//*[@id="thread_list"]/li/div/div[2]/div[1]/div[1]/a')
        # print(len(el_list))

        data_list = []
        for el in el_list:
            temp = {}
            temp['title'] = el.xpath('./text()')[0]
            temp['link'] = 'https://tieba.baidu.com' + el.xpath('./@href')[0]
            data_list.append(temp)

        # 获取下一页url
        try:
            next_url = 'https:' + html.xpath('//a[contains(text(),"下一页>")]/@href')[0]
        except:
            next_url = None

        return data_list, next_url

    def save_data(self, data_list):
        for data in data_list:
            print(data)

    def run(self):

        next_url = self.url
        while True:
            # 发送请求获取响应
            data = self.get_data(next_url)
            # 从响应中提取数据，数据和翻页用的url
            data_list, next_url = self.parse_data(data)
            self.save_data(data_list)
            print(next_url)
            # 判断是否结束
            if next_url == None:
                break


if __name__ == '__main__':
    tieba = Tieba("美食天下")
    tieba.run()