用的是beautiful soup 官网上的get start 部分 (自慕课)
# coding:utf8
import re
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="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,'html.parser',from_encoding='utf-8')
print "获取所有的链接"
links=soup.find_all('a')
for link in links :
print link.name,link['href'],link.get_text()
print "获取Lacie的链接"
link_node=soup.find('a',href="http://example.com/lacie")
print link_node.name,link_node['href'],link_node.get_text()
print "正则匹配"
link_node=soup.find('a',href=re.compile(r"ill"))#r的作用是不需要在字符串中用//表示/这种
print link_node.name,link_node['href'],link_node.get_text()
print "获取p段落文字"
link_node2=soup.find('p', class_="title")
print link_node2.name,link_node2.get_text()
然后补充一段自我修改后的爬取维基百科的最简陋代码。。。。
# coding:utf8
from bs4 import BeautifulSoup
import re
import urllib2
resp=urllib2.urlopen("https://en.wikipedia.org/wiki/Main_Page").read().decode("utf-8")
soup=BeautifulSoup(resp,"html.parser")
listUrls=soup.findAll("a",href=re.compile("^/wiki/"))
for url in listUrls:
if not re.search("\.(jpg|JPG)$",url['href']):
print (url["href"])