网页解析--BeautifulSoup练习

 # coding = utf-8

 # BeautifulSoup 主要功能是解析提取HTML数据

 # re lxml bs4

 # pip install Beautifulsoup4

 # from bs4 import BeautifulSoup

 html = '''

 <html><head><title>The Dormouse's story</title></head>

 <p class="title"><b>The Dormouse's story</b></p>

 <p class="story">Once upon a time there were three little sisters; and their names were

 <a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>,

 <a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and

 <a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;

 and they lived at the bottom of a well.</p>

 <p class="story">...</p>

 '''

 ############################################################################

 # BeautifulSoup部分

 #############################################################################

 # soup = BeautifulSoup(html, 'lxml')

 # 四大对象种类：Tag NavigableString Beautifulsoup Comment

 # print(soup.a)  # 获取a标签

 # print(soup.a.get('href'))   # 取a标签的属性,获得超链接

 # print(soup.a.text)  # 获取a标签下的文本，若a下有子标签，可能获取不到

 # print(soup.a.string)  # 获取a标签（包含a下的子标签）下的文本

 # 搜索文档：find  find_all 按照一定的过滤条件进行匹配

 # 字符串

 # print(soup.find_all('a'))  # 匹配整个文档中的a标签

 # print(soup.find_all(attrs={'class': 'title'})) # 匹配class为title的标签

 # #正则表达式

 # import re

 # print(soup.find_all(re.compile('^p')))  # 匹配以p开头的标签

 # print(soup.find_all(re.compile('y$')))  # 匹配以y结尾的标签

 # print(soup.find_all(re.compile('t')))  # 匹配包含t的标签

 # 列表

 # for tag in soup.find_all(['a', 'b']):  # 匹配a标签，b标签

 #     print(tag)

 # for tag in soup.find_all('p', class_='story'):  # 匹配class=story的p标签

 #     print(tag)

 # # 方法  给find_all传入一个方法作为过滤条件

 # def has_class_but_no_id(tag):

 #     """

 #     定义一个判断有class属性但是没有id属性的方法，作为过滤条件

 #     """

 #     return tag.has_attr('class') and not tag.has_attr('id')

 #

 # for tag in soup.find_all(has_class_but_no_id):

 #     print(tag)

 # css选择器

 # print(soup.select('title'))   # 通过标签名查找

 # print(soup.select('.sister')) # 通过class名查找

 # print(soup.select('#link1'))  # 通过id名查找

 # print(soup.select('p #link2'))  # 组合查找，id为link2的p标签

 # > 只能够一级一级向下查找

 # print(soup.select('body > p .sister')) # 查找body下类名为sister的p

 # 百度搜索python，对返回页面进行属性查找

 # import requests

 # url = 'http://www.baidu.com/s?wd=python'

 # response = requests.get(url)  # 获取的数据是网页源代码，未经过js渲染

 #

 # soup = BeautifulSoup(response.text, 'lxml')

 # 查找返回页面搜索到的结果

 # items = soup.find_all('div', class_='result c-container ')

 # 打印搜索结果

 # for item in items:

 #     print(item.select('h3 > a')[0].get('href')  # 取a标签

 #     print(item.select('h3 > a')[0].get_text())

 #################################################################################

 # xpath 部分

 # 通配符  /  //  @  # .  ..

 #   /表示从当前节点匹配  //整个文档匹配  @选取属性 *

 ########################################################################################

 html = '''

 <html><head><title>The Dormouse's story</title></head>

 <p class="title"><b>The Dormouse's story</b></p>

 <p class="story">Once upon a time there were three little sisters; and their names were

 <a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>,

 <a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and

 <a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;

 and they lived at the bottom of a well.</p>

 <p class="story">...</p>

 '''

 # from lxml import etree

 # e = etree.HTML(html)

 # for i in e.xpath('//p'):  # 整个文档中搜索p标签

 #     # print(i.xpath('string(.)'))  # 获取当前标签下所有文本（标签下套标签），包括下面子标签的文本

 #     print(i.text) # 匹配当前标签下的文本内容，不包含子标签

 """

 # for i in e.xpath('//p/@class'):  # 选取p的class属性

 # for i in e.xpath('//p[@class=title]'):  # 搜索class=title的p标签

 //title[@*]  匹配所有有属性的title标签

 """

 # 百度搜索python，用xpath查找

 import requests

 from lxml import etree

 url = 'http://www.baidu.com/s?wd=python'

 response = requests.get(url)  # 获取的数据是网页源代码

 tree = etree.HTML(response.text)

 # 查找返回页面搜索到的结果

 items = tree.xpath('//div[@class="result c-container "]')

 for item in items:

     # print(item.xpath('h3/a/@href'))

     print(item.xpath('h3/a')[0].xpath('string(.)'))
巴特西

网页解析--BeautifulSoup练习

最新文章

热门文章
