Python爬虫requests包和xpath包总结

最新推荐文章于 2023-06-19 08:54:19 发布

DedicateToAI

最新推荐文章于 2023-06-19 08:54:19 发布

阅读量1.4k

点赞数

分类专栏： nlp

本文链接：https://blog.csdn.net/DedicateToAI/article/details/86736875

版权

nlp 专栏收录该内容

4 篇文章

订阅专栏


import requests

# 这里的headers就是我们上图框中的headers
request_headers = {     'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
    'Accept-Encoding': 'gzip, deflate, br',
    'Accept-Language': "zh-CN,zh;q=0.9",
    'Cache-Control': 'no-cache',
    'cookie': '',
    'Pragma': 'no-cache',
    'Upgrade-Insecure-Requests': '1',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36 }'
    }#上图中的url
url = "https://www.douban.com/note/704821854/"
# 上图中的请求方法（get）
z = requests.get(url, headers=request_headers)
print(z.text)


from lxml import etree

sample1 = """<html>
  <head>
    <title>My page</title>
  </head>
  <body>
    <h2>Welcome to my <a href="#" src="x">page</a></h2>
    <p>This is the first paragraph.</p>
    <!-- this is the end -->
  </body>
</html>
"""

s1 = etree.HTML(sample1)
# 获取标题(两种方法都可以，第一种为绝对地址，第二种为相对地址)
print(s1)
print(s1.xpath('//title/text()'))  #相对地址
print(s1.xpath('/html/head/title/text()')) #绝对地址
print(s1.xpath('//h2/a/@src'))
print(s1.xpath('//@href'))
print(s1.xpath('//text()')) #获取所有的文本
print(s1.xpath('//comment()')) #获取所有的注释

sample2 = """
<html>
  <body>
    <ul>
      <li>Quote 1</li>
      <li>Quote 2 with <a href="...">link</a></li>
      <li>Quote 3 with <a href="...">another link</a></li>
      <li><h2>Quote 4 title</h2> ...</li>
    </ul>
  </body>
</html>
"""
s2 = etree.HTML(sample2)
print(s2.xpath('//li/text()'))
print(s2.xpath('//li[1]/text()'))
print(s2.xpath('//li[a or h2]/text()'))
print(s2.xpath('//a/text()|//h2/text()'))

sample3 = """<html>
  <body>
    <ul>
      <li id="begin"><a href="https://scrapy.org">Scrapy</a>begin</li>
      <li><a href="https://scrapinghub.com">Scrapinghub</a></li>
      <li><a href="https://blog.scrapinghub.com">Scrapinghub Blog</a></li>
      <li id="end"><a href="http://quotes.toscrape.com">Quotes To Scrape</a>end</li>
      <li data-xxxx="end" abc="abc"><a href="http://quotes.toscrape.com">Quotes To Scrape</a>end</li>
    </ul>
  </body>
</html>
"""
s3 = etree.HTML(sample3)
print(s3.xpath('//li/a[@href = "https://scrapy.org"]/text()'))
print(s3.xpath('//li[@abc="abc"]/text()'))


from lxml import etree
sample4 = u"""
<html>
  <head>
    <title>My page</title>
  </head>
  <body>
    <h2>Welcome to my <a href="#" src="x">page</a></h2>
    <p>This is the first paragraph.</p>
    <p class="test">
    编程语言<a href="#">python</a>
    <img src="#" alt="test"/>javascript
    <a href="#"><strong>C#</strong>JAVA</a>
    </p>
    <p class="content-a">a</p>
    <p class="content-b">b</p>
    <p class="content-c">c</p>
    <p class="content-d">d</p>
    <p class="econtent-e">e</p>
    <p class="heh">f</p>
    <!-- this is the end -->
  </body>
</html>
"""
s4 = etree.HTML(sample4)
print(s4.xpath('string(//p[@class = "test"])')) #标签中的标签文本
print(s4.xpath('//p[contains(@class, "content")]/text()'))  #包含

requests包对文件进行抓取，xpath包对html文件进行提取操作

string和text不能同时使用，string只能获取单个节点

参考资料：https://zhuanlan.zhihu.com/p/25572729