根据答案中的建议：subclassing beautifulsoup html parser, getting type error，我正在尝试使用类组合而不是子类化BeautifulSoup。
基本的Scraper类可以自行运行（至少在我的有限测试中）。
Scraper课程：
from BeautifulSoup import BeautifulSoup
import urllib2
class Scrape():
"""base class to be subclassed
basically a wrapper that providers basic url fetching with urllib2
and the basic html parsing with beautifulsoupץ
some useful methods are provided with class composition with BeautifulSoup.
for direct access to the soup class you can use the _soup property."""
def __init__(self,file):
self._file = file
#very basic input validation
#import re
#import urllib2
#from BeautifulSoup import BeautifulSoup
try:
self._page = urllib2.urlopen(self._file) #fetching the page
except (urllib2.URLError):
print ('please enter a valid url starting with http/https/ftp/file')
self._soup = BeautifulSoup(self._page) #calling the html parser
#BeautifulSoup.__init__(self,self._page)
# the next part is the class compostion part - we transform attribute and method calls to the BeautifulSoup class
#search functions:
self.find = self._soup.find
self.findAll = self._soup.findAll
self.__iter__ = self._soup.__iter__ #enables iterating,looping in the object
self.__len__ = self._soup.__len__
self.__contains__ = self._soup.__contains__
#attribute fetching and setting - __getattr__ implented by the scraper class
self.__setattr__ = self._soup.__setattr__
self.__getattribute__ = self._soup.__getattribute__
#Called to implement evaluation of self[key]
self.__getitem__ = self._soup.__getitem__
self.__setitem__ = self._soup.__setitem__
self.__delitem__ = self._soup.__delitem__
self.__call__ = self._soup.__call__#Called when the instance is “called” as a function
self._getAttrMap = self._soup._getAttrMap
self.has_key = self._soup.has_key
#walking the html document methods
self.contents = self._soup.contents
self.text = self._soup.text
self.extract = self._soup.extract
self.next = self._soup.next
self.parent = self._soup.parent
self.fetch = self._soup.fetch
self.fetchText = self._soup.fetchText
self.findAllNext = self._soup.findAllNext
self.findChild = self._soup.findChild
self.findChildren = self._soup.findChildren
self.findNext = self._soup.findNext
self.findNextSibling = self._soup.findNextSibling
self.first = self._soup.first
self.name = self._soup.name
self.get = self._soup.get
self.getString = self._soup.getString
# comparison operators or similiar boolean checks
self.__eq__ = self._soup.__eq__
self.__ne__ = self._soup.__ne__
self.__hash__ = self._soup.__hash__
self.__nonezero__ = self._soup.__nonzero__ #not sure
# the class represntation magic methods:
self.__str__ = self._soup.__str__
self.__repr__ =self._soup.__repr__
#self.__dict__ = self._soup.__dict__
def __getattr__(self,method):
"""basically this 'magic' method transforms calls for unknown attributes to
and enables to traverse the html document with the .notation.
for example - using instancename.div will return the first div.
explantion: python calls __getattr__ if It didn't find any method or attribute correspanding to the call.
I'm not sure this is a good or the right use for the method """
return self._soup.find(method)
def clean(self,work=False,element=False):
"""clean method that provides:basic cleaning of head,scripts etc
input 'work' soup object to clean from unneccesary parts:scripts,head,style
has optional variable:'element' that can get a tuple of element
that enables to override what element to clean"""
self._work = work or self._soup
self._cleanelements=element or ("head","style","script")
#for elem in self._work.findAll(self._cleanelements):
for elem in self.findAll(self._cleanelements):
elem.extract()
但是当我将它子类化时，我会得到某种递归循环，我只能想象。
这是子类（相关部分）：
class MainTraffic(Scrape):
"""class traffic - subclasses the Scrape class
inputs a page url and a category"""
def __init__(self, file, cat, caller = False):
if not caller:
self._file = file
#import urllib2
#self._request = urllib2.Request(self._file)# request to post the show all questions
Scrape.__init__(self,self._file)
self.pagecat = cat
self.clean(self)
self.cleansoup = self.cleantotable(self)
self.fetchlinks(self.cleansoup)
#self.populatequestiondic()
#del (self.cleansoup)
def cleantotable(self):
pass
def fetchlinks(self,fetch):
pass
def length(self):
from sqlalchemy import func
self.len = session.query(func.count(Question.id)).scalar()
return int(self.len)
def __len__(self):
return self.length()
def __repr__(self):
self.repr = "traffic theory question, current number of questions:{0}".format(self.length())
return self.repr
def __getitem__(self,key):
try:
self._item = session.query(Question).filter_by(question_num=key).first()
return self._item
except (IndexError, KeyError):
print "no such key:{0}".format(key)
以下是错误消息：
File "C:\Python27\learn\traffic.py", line 117, in __init__
Scrape.__init__(self,self._file)
File "C:\Python27\learn\traffic.py", line 26, in __init__
self._soup = BeautifulSoup(self._page) #calling the html parser
File "C:\Python27\learn\traffic.py", line 92, in __getattr__
return self._soup.find(method)
File "C:\Python27\learn\traffic.py", line 92, in __getattr__
return self._soup.find(method)
File "C:\Python27\learn\traffic.py", line 92, in __getattr__
return self._soup.find(method)
RuntimeError: maximum recursion depth exceeded
我怀疑问题是我误导了__getattr__，但我无法弄清楚应该改变什么。
答案 0 :(得分：3)
您的代码无效，因为__getattr__()在初始化之前访问self._soup。这是因为四条看似无害的线条：
try:
self._page = urllib2.urlopen(self._file)
except (urllib2.URLError):
print ('please enter a valid url starting with http/https/ftp/file')
为什么你会抓住异常并且实际上没有处理它？</ p>
下一行访问self._page，如果urlopen（）抛出异常，则还没有设置：
self._soup = BeautifulSoup(self._page)
由于尚未设置，因此访问它会调用访问__getattr__()的{{1}}，该self._soup尚未设置，因此会访问__getattr__。
最简单的“修复”是特殊情况_soup，以防止无限递归。另外，__getattr__似乎更有意义在汤上进行正常的属性查找：
def __getattr__(self,attr):
if attr == "_soup":
raise AttributeError()
return getattr(self._soup,attr)
复制所有方法不太可能奏效，而且似乎完全忽略了课程构成的重点。