requests和lxml实现爬虫的实例教程

# requests模块来请求页面
# lxml模块的html构建selector选择器(格式化响应response)
# from lxml import html
# import requests

# response = requests.get(url).content

# selector = html.formatstring(response)

# hrefs = selector.xpath('/html/body//div[@class='feed-item _j_feed_item']/a/@href')

# 以url = 'https://HdhCmsTestmafengwo.cn/gonglve/ziyouxing/2033.html'为例子

# python 2.7import requestsfrom lxml import htmlimport os 

查看更多关于requests和lxml实现爬虫的实例教程的详细内容...