python爬虫-网页数据提取

AI从入门到实践2023-08-27 23:45
python 复制代码
import requests
#headers = 网页右键->Network->最下面的User-Agent复制。
headers = {"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36"}
#你想要的网址
url = "https://www.xinpianchang.com/discover/article?from=navigator"
response = requests.get(url, headers=headers)
print(response)# 打印200 说明访问成功
#下面是正式的数据提取，构建xpath的对象
from lxml import etree
tree = etree.HTML(response.text)#页面的元素树
##示例1 标题
elements = tree.xpath('//h2[@class="truncate block"]')#在Elements寻找你想要的元素，可以在页面移动#光标
for element in elements:
    print(element.text)
##也可以在elements中右键copy xpath，这里需要分析一下，将复制的xpath删除一部分
print(tree.xpath('//*[@id="__next"]/section/main/div/div/div/div/div/a/div/ul/li[1]/span[2]')[0].text)
print(tree.xpath('//*[@id="__next"]/section/main/div/div/div/div/div/a/div/ul/li[2]/span[2]')[0].text)
print(tree.xpath('/html/body/div/section/main/div/div/div/div/div/div/a/h2')[1].text)