爬虫requestXpath模块,继承requests模块,增加xpath功能

# 安装 pip install requestXpath

# 导入

from requestXpath import requests

# 使用样例

response = requests.get(url='http://www.runoob.com/python3/python3-tutorial.html')

print(response) # 返回response对象

print(response.status_code) # 返回response状态码

# print(response.text) # 返回response源码

# print(response.json) # 返回response Json

item = {}

TreeItem = response.tree # 实例化tree

title = TreeItem.xpath("//div[@id='content']/h1") # xpath提取(默认'.//text()', 支持'/@href')

filter_title = TreeItem.xpath("//div[@id='content']/h1|//div[@id='content']/h2", filter="div[@id='content']/h2") # xpath提取, 过滤器, 开头不需要'//'

re_title = TreeItem.xpath("//div[@id='content']/h1", rule='Python 3(.*)') # xpath提取, 支持正则

titleXpathObj = TreeItem.xxpath("//div[@id='content']/h1/text()") # 原生xpath提取

link = TreeItem.xpath("//div[@id='leftcolumn']/a/@href", is_list=True) # xpath提取(is_list:True返回列表)

item['标题'], item['正则标题'], item['链接'], item['titleXpathObj'], item['filter_title'] = title, re_title, link, titleXpathObj, filter_title

print(item)

————————————————

版权声明：本文为CSDN博主「Dwyane Wade.」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。

原文链接：