1.在线文档 http://www.crummy.com/software/BeautifulSoup/bs4/doc/
2.常用方法
- 选择器 find_all(name, attrs, recursive, text, limit, **kwargs)
3.主要调用方法
4.完整代码
#-*- coding:utf-8 -*-
from bs4 import BeautifulSoup;
def main():
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="cla" id="link3">Tillie</a>;
and they lived at the bottom of a well.</p>
<p class="story">...</p>
"""
# print html_doc
soup = BeautifulSoup(html)
print soup.get_text() #获得文本
print soup.find_all('title') #获取标题
print soup.find_all('a') #获取链接<a>
print soup.find_all(id="link2") #根据ID来获取HTML元素
print soup.find_all("a",class_="cla") #根据class来获取HTML元素
#根据class属性来选择
print soup.find_all("a", class_="sister")
print soup.select("p.title")
#多重属性来选择
print soup.find_all("a", attrs={"class": "sister"})
#根据文本来选择
print soup.find_all(text="Elsie")
print soup.find_all(text=["Tillie", "Elsie", "Lacie"])
#限制查询的个数
print soup.find_all("a", limit=2)
if __name__ == '__main__':
main()