python獲取頁面所有a標籤下href的值
阿新 • • 發佈:2018-12-19
參考下面的連結中的內容:
# -*- coding:utf-8 -*- #python 2.7 #http://tieba.baidu.com/p/2460150866 #標籤操作 from bs4 import BeautifulSoup import urllib.request import re #如果是網址,可以用這個辦法來讀取網頁 #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" class="sister" id="xiaodeng"><!-- 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>; <a href="http://example.com/lacie" 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') #文件物件 #查詢a標籤,只會查找出一個a標籤 #print(soup.a)#<a class="sister" href="http://example.com/elsie" id="xiaodeng"><!-- Elsie --></a> for k in soup.find_all('a'): print(k) print(k['class'])#查a標籤的class屬性 print(k['id'])#查a標籤的id值 print(k['href'])#查a標籤的href值 print(k.string)#查a標籤的string 如果,標籤<a>中含有其他標籤,比如<em>..</em>,此時要提取<a>中的資料,需要用k.get_text()
soup = BeautifulSoup(html, 'html.parser') #文件物件 #查詢a標籤,只會查找出一個a標籤
for k in soup.find_all('a'): print(k) print(k['class'])#查a標籤的class屬性 print(k['id'])#查a標籤的id值 print(k['href'])#查a標籤的href值 print(k.string)#查a標籤的string
如果,標籤<a>中含有其他標籤,比如<em>..</em>,此時要提取<a>中的資料,需要用k.get_text()
通常我們使用下面這種模式也是能夠處理的,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)