我正在尝试使用 HTMLParser 从 HTML 页面读取标题标签。但是我收到上述错误。我的类(class)如下所示:
readtitle.py
from HTMLParser import HTMLParser
import urllib
class MyHTMLParser(HTMLParser):
def __init__(self, url):
HTMLParser.__init__(self)
self.url = url
self.data = urllib.urlopen(url).read()
self.feed(self.data)
self.intitle = ""
self.mytitle = ""
def handle_starttag(self, tag, attrs):
self.intitle = tag == "title"
def handle_data(self, data):
if self.intitle:
self.mytitle = data
return self.mytitle
我使用以下命令运行代码并收到错误:
import urllib
import readtitle
parser = readtitle.MyHTMLParser("http://docs.python.org/tutorial/classes.html")
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "readtitle.py", line 10, in __init__
self.feed(self.data)
File "/usr/lib/python2.6/HTMLParser.py", line 108, in feed
self.goahead(0)
File "/usr/lib/python2.6/HTMLParser.py", line 142, in goahead
if i < j: self.handle_data(rawdata[i:j])
File "readtitle.py", line 18, in handle_data
if self.intitle:
AttributeError: MyHTMLParser instance has no attribute 'intitle'
最佳答案
在运行 self.intitle = ""之前，您运行 。self.feed()，从而调用 handle_data() (根据跟踪判断)
修复:
self.url = url
self.data = urllib.urlopen(url).read() # Perhaps there should be a decode() here?
self.intitle = False
self.mytitle = ""
self.feed(self.data)
----------------------------------------------------
调试始终是最重要的部分。运行此代码并查看它打印的内容。
from HTMLParser import HTMLParser
import urllib, sys
class MyHTMLParser(HTMLParser):
def __init__(self, url):
HTMLParser.__init__(self)
self.url = url
self.data = urllib.urlopen(url).read()
self.in_title = False
self.title = ''
self.feed(self.data)
def handle_starttag(self, tag, attrs):
if tag == 'body': sys.exit('Found <body>, quitting') # Much easier to look at
self.in_title = (tag == 'title')
print 'Handled start of', tag, ' in_title is', self.in_title
def handle_endtag(self, tag):
print 'Handled end of', tag
def handle_data(self, data):
print "Handling data:", repr(data)
if self.in_title:
print "Apparently, we are in a <title> tag. self.title is now", repr(data)
self.title = data
print data
return self.title
parser = MyHTMLParser("http://www.york.ac.uk/teaching/cws/wws/webpage1.html")
为方便起见，相关页面的 HTML:
<HMTL>
<HEAD>
<TITLE>webpage1</TITLE>
</HEAD>
<BODY BGCOLOR="FFFFFf" LINK="006666" ALINK="8B4513" VLINK="006666">
关于python - MyHTMLParser 实例没有属性 'intitle'，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/11409945/