我在python中为非常简单的网络爬虫编写了以下程序,但是当我运行它时它会返回给我 'NoneType'对象不可调用',你能帮我吗?
import BeautifulSoup
import urllib2
def union(p,q):
for e in q:
if e not in p:
p.append(e)
def crawler(SeedUrl):
tocrawl=[SeedUrl]
crawled=[]
while tocrawl:
page=tocrawl.pop()
pagesource=urllib2.urlopen(page)
s=pagesource.read()
soup=BeautifulSoup.BeautifulSoup(s)
links=soup('a')
if page not in crawled:
union(tocrawl,links)
crawled.append(page)
return crawled
crawler('http://www.princeton.edu/main/')
答案 0 :(得分:5)
[更新]以下是完整的项目代码
https://bitbucket.org/deshan/simple-web-crawler
<强> [ANWSER] 强>
soup('a')返回完整的html标记。
<a href="http://itunes.apple.com/us/store">Buy Music Now</a>
所以 urlopen 会出错 'NoneType'对象不可调用'。你需要提取唯一的url / href。
links=soup.findAll('a',href=True)
for l in links:
print(l['href'])
您还需要验证网址。请参阅关注
How do you validate a URL with a regular expression in Python?
Python - How to validate a url in python ? (Malformed or not)
我再次建议您使用python集代替Arrays.you可以轻松添加,省略重复的网址。
请尝试以下代码:
import re
import httplib
import urllib2
from urlparse import urlparse
import BeautifulSoup
regex = re.compile(
r'^(?:http|ftp)s?://' # http:// or https://
r'(?:(?:[A-Z0-9](?:[A-Z0-9-]{0,61}[A-Z0-9])?\.)+(?:[A-Z]{2,6}\.?|[A-Z0-9-]{2,}\.?)|' #domain...
r'localhost|' #localhost...
r'\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})' # ...or ip
r'(?::\d+)?' # optional port
r'(?:/?|[/?]\S+)$', re.IGNORECASE)
def isValidUrl(url):
if regex.match(url) is not None:
return True;
return False
def crawler(SeedUrl):
tocrawl=[SeedUrl]
crawled=[]
while tocrawl:
page=tocrawl.pop()
print 'Crawled:'+page
pagesource=urllib2.urlopen(page)
s=pagesource.read()
soup=BeautifulSoup.BeautifulSoup(s)
links=soup.findAll('a',href=True)
if page not in crawled:
for l in links:
if isValidUrl(l['href']):
tocrawl.append(l['href'])
crawled.append(page)
return crawled
crawler('http://www.princeton.edu/main/')