# -*- coding:utf-8 -*- #python 2.7 #http://tieba.baidu.com/p/2460150866 #标签操作 from bs4 import BeautifulSoup import urllib.request import re #如果是网址,可以用这个办法来读取网页 #html_doc = "http://tieba.baidu.com/p/2460150866" #req = urllib.request.Request(html_doc) #webpage = urllib.request.urlopen(req) #html = webpage.read() html=""" html>head>title>The Dormouse's story/title>/head> body> p class="title" name="dromouse">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" rel="external nofollow" rel="external nofollow" class="sister" id="xiaodeng">!-- Elsie -->/a>, a href="http://example.com/lacie" rel="external nofollow" rel="external nofollow" class="sister" id="link2">Lacie/a> and a href="http://example.com/tillie" rel="external nofollow" class="sister" id="link3">Tillie/a>; a href="http://example.com/lacie" rel="external nofollow" rel="external nofollow" class="sister" id="xiaodeng">Lacie/a> and they lived at the bottom of a well./p> p class="story">.../p> """ soup = BeautifulSoup(html, 'html.parser') #文档对象 #查找a标签,只会查找出一个a标签 #print(soup.a)#a class="sister" href="http://example.com/elsie" rel="external nofollow" rel="external nofollow" id="xiaodeng">!-- Elsie -->/a> for k in soup.find_all('a'): print(k) print(k['class'])#查a标签的class属性 print(k['id'])#查a标签的id值 print(k['href'])#查a标签的href值 print(k.string)#查a标签的string
如果,标签a>中含有其他标签,比如em>../em>,此时要提取a>中的数据,需要用k.get_text()
soup = BeautifulSoup(html, 'html.parser') #文档对象 #查找a标签,只会查找出一个a标签 for k in soup.find_all('a'): print(k) print(k['class'])#查a标签的class属性 print(k['id'])#查a标签的id值 print(k['href'])#查a标签的href值 print(k.string)#查a标签的string
如果,标签a>中含有其他标签,比如em>../em>,此时要提取a>中的数据,需要用k.get_text()
通常我们使用下面这种模式也是能够处理的,下面的方法使用了get()。
html = urlopen(url) soup = BeautifulSoup(html, 'html.parser') t1 = soup.find_all('a') print t1 href_list = [] for t2 in t1: t3 = t2.get('href') href_list.append(t3)
补充:python爬虫获取任意页面的标签和属性(包括获取a标签的href属性)
# coding=utf-8 from bs4 import BeautifulSoup import requests # 定义一个获取url页面下label标签的attr属性的函数 def getHtml(url, label, attr): response = requests.get(url) response.encoding = 'utf-8' html = response.text soup = BeautifulSoup(html, 'html.parser'); for target in soup.find_all(label): try: value = target.get(attr) except: value = '' if value: print(value) url = 'https://baidu.com/' label = 'a' attr = 'href' getHtml(url, label, attr)
以上为个人经验,希望能给大家一个参考,也希望大家多多支持脚本之家。如有错误或未考虑完全的地方,望不吝赐教。