python爬虫学习

喜欢ヅ旅行 2022-10-05 04:48 326阅读 0赞

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2xpdWxhbmc2OA_size_16_color_FFFFFF_t_70]

https://blog.csdn.net/bookssea/article/details/107309591?ops\_request\_misc=%257B%2522request%255Fid%2522%253A%2522162293641016780262511027%2522%252C%2522scm%2522%253A%252220140713.130102334…%2522%257D&request\_id=162293641016780262511027&biz\_id=0&utm\_medium=distribute.pc\_search\_result.none-task-blog-2alltop\_positive~default-1-107309591.first\_rank\_v2\_pc\_rank\_v29&utm\_term=%E7%88%AC%E8%99%AB&spm=1018.2226.3001.4187

from bs4 import BeautifulSoup
    from urllib import request
    #获取网页内容
    base_url = 'https://www.baidu.com/more/'
    response  = request.urlopen(base_url)
    html = response.read()
    # print(html)
    
    #数据解析（从页面当中提取数据）
    #创建bs4对象
    soup = BeautifulSoup(html,'lxml')
    #格式化输出对象中的内容
    content = soup.prettify()
    # print(content)
    
    #提取页面当中的指定内容
    # print(soup.body)  #获取title内容
    
    
    #一  只能匹配到第一个标签内容
    #1.tag(name)
    # print(soup.name)   #输出文档类型
    # print(soup.div.name) #输出标签名
    #2attrs
    # print(soup.title.attrs)
    # print(soup.img.attrs)
    
    #3修改属性值
    img = soup.img.attrs
    # print(img)
    domain = 'http://www.langlang2017.com'
    img["src"] = domain+ img["src"]
    # print(img)
    
    #4删除
    img= soup.img.attrs
    # print(img)
    del  img["alt"]
    # print(img)
    
    #二
    #1获取文本
    # print(soup.title)
    # print(soup.title.attrs)
    # print(soup.title.name)
    #格式：标签名.string
    # print(soup.title.string)
    
    #三 标签名.contents 获取子节点列表
    # head = soup.head.contents
    # print(head)
    # print(head[3])
    
    #标签名.children  --子节点
    # head_children = soup.head.children
    # for i in head_children:
    #     print(i)
    
    #便签名.descendants  --子孙节点
    print(soup.div)
    for i in soup.div.descendants:
        print(i)
    
    #搜索文档 find_all()
    # print(soup.meta)  #只能获取一个
    # for i in soup.find_all('meta'):
    #     print(i)
    
    #标签列表
    # print(soup.find_all(["h1","h2"]))
    
    #关键词
    # print(soup.find_all(id='weixin'))
    
    #四 css选择器 soup.select()
    #通过类名查找
    # print(soup.select('.logo'))
    #通过标签名查找
    # print(soup.select('a'))
    #通过id查找
    # print(soup.select('#weixin'))

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2xpdWxhbmc2OA_size_16_color_FFFFFF_t_70 1]https://blog.csdn.net/wmy0217\_/article/details/117908246?utm\_medium=distribute.pc\_category.none-task-blog-hot-7.nonecase&depth\_1-utm\_source=distribute.pc\_category.none-task-blog-hot-7.nonecase

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2xpdWxhbmc2OA_size_16_color_FFFFFF_t_70]: /images/20221005/cd1f32666df243b5aed207a018392927.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2xpdWxhbmc2OA_size_16_color_FFFFFF_t_70 1]: /images/20221005/bf4acbee321c4819b7d25b6f559be3df.png