从0开始学爬虫7之BeautifulSoup模块的简单介绍
参考文档：
https://www.crummy.com/software/BeautifulSoup/bs4/doc.zh/
# 安装 beautifulsoup4
(pytools) D:\python\pytools>pip install beautifulsoup4
# coding=utf-8 from bs4 import BeautifulSoup as bs import re html_doc = """ <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> """ soup = bs(html_doc, "html.parser") # print(soup.prettify()) # print(soup.title.string) # print(soup.a) # print(soup.find(id='link2')) # print(soup.find(id='link2').string) # print(soup.find(id='link2').get_text()) # 获取所有a标签的内容 # for link in soup.find_all('a'): # print(link.get_text()) # 使用string获取不到p标签的内容 # print(soup.find("p", {"class": "story"}).get_text()) # 查找所有以b开头的标签 # for tag in soup.find_all(re.compile("^b")): # print(tag.get_text()) # 查找所有的a标签中href以 http://example.com开头的数据，其中的.号代表任意字符，如果需要 表示点号本身可以用\转义 href=re.compile(r"^http://example\.com/") data = soup.find_all("a", href=re.compile(r"^http://example.com/")) print(data)
