python利用beautifulSoup实现爬虫

# coding=utf-8
import urllib
from bs4 import BeautifulSoup

url ='http://www.baidu.com/s'
values ={'wd':'网球'}
encoded_param = urllib.urlencode(values)
full_url = url +'?'+ encoded_param
response = urllib.urlopen(full_url)
soup =BeautifulSoup(response)
alinks = soup.find_all('a')

soup = BeautifulSoup('
Extremely bold
')
tag = soup.b
type(tag)
#

tag.attrs
# {u'class': u'boldest'}

tag['class'] = 'verybold'
tag['id'] = 1
tag
#Extremely bolddel tag['class']
del tag['id']
tag
#Extremely boldtag['class']
# KeyError: 'class'
print(tag.get('class'))
# None

html_doc = """The Dormouse's storyThe Dormouse's storyOnce upon a time there were three little sisters; and their names wereElsie,Lacie andTillie;
and they lived at the bottom of a well...."""

from bs4 import BeautifulSoup
soup = BeautifulSoup(html_doc)

soup.head
#The Dormouse's storysoup.title
#The Dormouse's storysoup.body.b
# The Dormouse's storysoup.a
# Elsiesoup.find_all('a')
# [Elsie,
# Lacie,
# Tillie]
head_tag = soup.head
head_tag
#The Dormouse's storyhead_tag.contents
[The Dormouse's story]

title_tag = head_tag.contents[0]
title_tag
#The Dormouse's storytitle_tag.contents
# [u'The Dormouse's story']
len(soup.contents)
# 1
soup.contents[0].name
# u'html'
text = title_tag.contents[0]
text.contents

for child in title_tag.children:
  print(child)
head_tag.contents
# [The Dormouse's story]
for child in head_tag.descendants:
  print(child)
#The Dormouse's story# The Dormouse's story

len(list(soup.children))
# 1
len(list(soup.descendants))
# 25
title_tag.string
# u'The Dormouse's story'