解析库-beautifulsoup模块
# -*- coding: utf-8 -*- from bs4 import BeautifulSoup # 安装:pip install beautifulsoup4 # Beautiful Soup支持Python标准库中的HTML解析器,还支持一些第三方的解析器,其中一个是 lxml .根据操作系统不同,可以选择下列方法来安装lxml: # 安装解析器:pip install lxml # 另一个可供选择的解析器是纯Python实现的 html5lib , html5lib的解析方式与浏览器相同,可以选择下列方法来安装html5lib: # 安装解析器:pip install html5lib # 基本使用:直接连接网页太麻烦,直接拿下载好的网页做测试; # html_doc = """ # <html><head><title>The Dormouse's story</title></head> # <body> # <p class="title"><b>The Dormouse's story</b></p> # <p class="title"><b>The Dormouse's story2</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> # """ # 基本使用:容错处理,文档的容错能力指的是在HTML代码不完整的情况下,使用该模块可以识别错误 # 使用该Beautifulsoup解析上述代码,能够得到一个bearutifulsoup对象,并且按照标准格式输出 # soup = BeautifulSoup(html_doc,"lxml") # 具有容错功能 # print(soup.prettify()) #可以处理好缩进,按照标准格式输出 # soup = BeautifulSoup(html_doc,"html.parser") # print(soup) # 遍历文档树 # 1、用法 # soup = BeautifulSoup(open("a.html"),"lxml") # soup = BeautifulSoup(html_doc,"lxml") # print(soup.p) #存在多个相同的标签只返回第一个 # print(soup.a) # 2、获取标签的名称 # print(soup.p.name) #获取该标签的名称,不过有点多此一举 # 3、获取标签属性 # print(soup.p.attrs) # 4、获取标签的内容 # print(soup.p.string) # p下边没有子元素的时候返回他的文本,否则返回none # print(soup.p.strings) # 拿到p的生成器对象 # print(soup.p.text) #去文本内容 # for line in soup.stripped_strings: # print(line) # 去掉空白,打印p的文本内容 # 5、嵌套选择: # print(soup.head.title.string) #标签嵌套 # print(soup.body.a.string) # 6、子节点,子孙接点 # print(soup.p.contents) #取p下边的所有子节点 # print(soup.p.children) #得到一个迭代器,包含p下的所有子节点 # for i in soup.p.children: # print(i) # for i,child in enumerate(soup.p.children): # print(i,child) # print(soup.p.descendants) # for i,child in enumerate(soup.p.descendants): # print(i,child) # 获取子孙接点 # 7、父节点,祖先接点 # print(soup.a.parent) #获取a的父节点 # print(list(soup.a.parents)) #获取到a的所有祖先元素、 # 8、兄弟接点 # print(soup.a.next_sibling) #h获取a的上一个兄弟 # print(soup.a.previous_sibling) # h获取a的下一个兄弟 # print(list(soup.a.next_siblings)) #所有的兄弟列表 # print(soup.a.previous_siblings) #兄弟的生成器对象 # 搜索文档树 # 五种过滤器: 字符串、正则表达式、列表、True、方法 # 1、字符串:标签名 # print(soup.find_all("b")) # 2、正则表达式 # import re # print(soup.find_all(re.compile("^b"))) # 3、列表 # print(soup.find_all(["a","b"])) # 找到a或b # 4、True # print(soup.find_all(True)) #找到所有的tag # for tag in soup.find_all(True): # print(tag.name) #找到所有的标签名 # 5、方法:如果没有合适过滤器,那么还可以定义一个方法,方法只接受一个元素参数 ,如果这个方法返回 True 表示当前元素匹配并且被找到,如果不是则反回 False # def has_class_but_no_id(tag): # return tag.has_attr("class") and not tag.has_attr("id") # # print(soup.find_all(has_class_but_no_id)) # find_all( name , attrs , recursive , text , **kwargs ) html_doc = """ <html><head><title>The Dormouse's story</title></head> <body> <p id="my p" class="title"><b id="bbb" class="boldest">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> """ import re from bs4 import BeautifulSoup soup=BeautifulSoup(html_doc,'lxml') # 1、name: 搜索name参数的值可以使任一类型的 过滤器 ,字符窜,正则表达式,列表,方法或是 True # print(soup.find_all(name=re.compile("^t"))) # 2、keyword: key=value的形式,value可以是过滤器:字符串 , 正则表达式 , 列表, True . # print(soup.find_all(id=re.compile("my"))) # print(soup.find_all(href=re.compile("lacie"),id=re.compile("\d"))) # print(soup.find_all(id=True))? # # 有些tag属性在搜索不能使用,比如HTML5中的 data-* 属性: # data_soup = BeautifulSoup('<div data-foo="value">foo!</div>','lxml') # # data_soup.find_all(data-foo="value") #报错:SyntaxError: keyword can't be an expression # # 但是可以通过 find_all() 方法的 attrs 参数定义一个字典参数来搜索包含特殊属性的tag: # print(data_soup.find_all(attrs={"data-foo": "value"})) # # [<div data-foo="value">foo!</div>] # 3、按照类名查找,注意关键字是class_,class_=value,value可以是五种选择器之一 # print(soup.find_all('a',class_='sister')) #查找类为sister的a标签 # print(soup.find_all('a',class_='sister ssss')) #查找类为sister和sss的a标签,顺序错误也匹配不成功 # print(soup.find_all(class_=re.compile('^sis'))) #查找类为sister的所有标签 # 4、attrs # print(soup.find_all("p",attrs={"class":"story"})) # 5、text: 值可以是:字符,列表,True,正则 # print(soup.find_all(text='Elsie')) # print(soup.find_all('a',text='Elsie')) # 6、limit参数:如果文档树很大那么搜索会很慢.如果我们不需要全部结果,可以使用 limit 参数限制返回结果的数量.效果与SQL中的limit关键字类似,当搜索到的结果数量达到 limit 的限制时,就停止搜索返回结果?? # print(soup.find_all("a",limit=2)) # 7、recursive:调用tag的 find_all() 方法时,Beautiful Soup会检索当前tag的所有子孙节点,如果只想搜索tag的直接子节点,可以使用参数 recursive=False . # print(soup.html.find_all("a")) # print(soup.find_all("a")) # print(soup.html.find_all("a",recursive=False)) # find( name , attrs , recursive , text , **kwargs ) # 和find_all类似 # html_doc = """ # <html><head><title>The Dormouse's story</title></head> # <body> # <p class="title"> # <b>The Dormouse's story</b> # Once upon a time there were three little sisters; and their names were # <a href="http://example.com/elsie" class="sister" id="link1"> # <span>Elsie</span> # </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>; # <div class='panel-1'> # <ul class='list' id='list-1'> # <li class='element'>Foo</li> # <li class='element'>Bar</li> # <li class='element'>Jay</li> # </ul> # <ul class='list list-small' id='list-2'> # <li class='element'><h1 class='yyyy'>Foo</h1></li> # <li class='element xxx'>Bar</li> # <li class='element'>Jay</li> # </ul> # </div> # and they lived at the bottom of a well. # </p> # <p class="story">...</p> # """ # from bs4 import BeautifulSoup # soup=BeautifulSoup(html_doc,'lxml') # css选择器 # 1、css选择器 # print(soup.select(".sister span")) # print(soup.select("#link1")) # print(soup.select("#link1 span")) # print(soup.select("#list-2 .element.xxx")) # print(soup.select("#list-2")[0].select(".element")) # 2、获取属性 # print(soup.select("#list-2 h1")[0].attrs) # 3、获取内容 # print(soup.select("#list-2 h1")[0].get_text())
import requests from bs4 import BeautifulSoup html_doc = """ <html><head><title>The Dormouse's story</title></head> <body> <p class="title"><b>The Dormouse's story</b></p> <p class="title"><b>The Dormouse's story2</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> """ soup = BeautifulSoup(html_doc,"lxml") # print(soup) #完整的HTML文档 # print(soup.text) #所有网页的文本信息 # print(soup.p.attrs) #获取到第一个p的属性值 # print(soup.find_all("p")) #获取到所有的p标签的标签信息 p_s = soup.find_all("p") # for p in p_s: #循环每一个p标签 # print(p.text) #打印每个p标签的文本信息 # for p in p_s: # print(p.a) #打印p下边的a标签 # a_l = soup.find("a") # print(a_l.get("href")) #获取到a标签的href属性 # a_s = soup.find_all("a",attrs={"class":"sister"}) #找到所有具有sister属性的a标签 # print(a_s) # a_t = soup.find_all("a",text="Elsie") #获取到a标签的文本是elsie的标签 # print(a_t) # a_ls = soup.find_all("a") # for a in a_ls: # print(a.get("href")) # select_a = soup.select("#link1")[0] # print(select_a)
修改文档树:中文链接
https://www.crummy.com/software/BeautifulSoup/bs4/doc/index.zh.html#id40
本文来自博客园,作者:一石数字欠我15w!!!,转载请注明原文链接:https://www.cnblogs.com/52-qq/p/8316537.html