BeautifulSoup随笔

BeautifulSoup是一个类html

b = BeautifulSoup(html)java

b对象有与html结构相关的各类方法和和属性。app

a = b.findAll('a')得到标签的对象dom

a对象又有关于属性的各类方法和属性吧url

获取某网页的全部链接:spa

from bs4 import BeautifulSoup
import urllib.request
import sys

url = 'http://news.163.com/'

#获取网页html
html = urllib.request.urlopen(url).read()
html = html.decode('gbk')

#经过BeautifulSoup提取href
a = BeautifulSoup(html).findAll('a')
count = 0
err_a_list = []
for i in a:
    try:
        if i and i.attrs['href'][0] != 'j':  #排除href = java..
            print(i.attrs['href'])
    except Exception as e:            #当没有href属性或属性值为空时会报错,捕获以防止循环被中断
        print(e)
        err_a_list.append(i)
        count += 1
print("\n"*8)
for i in err_a_list:
    print(i)
    print()
print(count)

 

对网址没有域名以及锚点等href处理:.net

 http://blog.csdn.net/huangxiongbiao/article/details/45584407code

    # 将形如#comment-text的锚点补全成http://www.ruanyifeng.com/blog/2015/05/co.html,将形如/feed.html补全为http://www.ruanyifeng.com/feed.html
    alist = map(lambda i: proto + '://' + domain + i if i[0] == '/' else url + i if i[0] == '#' else i, alist)

 

shtm

相关文章
相关标签/搜索