I am using pickle to save an object graph by dumping the root. When I load the root it has all the instance variables and connected object nodes. However I am saving all the nodes in a class variable of type dictionary. The class variable is full before being saved but after I unpickle the data it is empty.
Here is the class I am using:
class Page():
__crawled = {}
def __init__(self, title = '', link = '', relatedURLs = []):
self.__title = title
self.__link = link
self.__relatedURLs = relatedURLs
self.__related = []
@property
def relatedURLs(self):
return self.__relatedURLs
@property
def title(self):
return self.__title
@property
def related(self):
return self.__related
@property
def crawled(self):
return self.__crawled
def crawl(self,url):
if url not in self.__crawled:
webpage = urlopen(url).read()
patFinderTitle = re.compile('<title>(.*)</title>')
patFinderLink = re.compile('<link rel="canonical" href="([^"]*)" />')
patFinderRelated = re.compile('<li><a href="([^"]*)"')
findPatTitle = re.findall(patFinderTitle, webpage)
findPatLink = re.findall(patFinderLink, webpage)
findPatRelated = re.findall(patFinderRelated, webpage)
newPage = Page(findPatTitle,findPatLink,findPatRelated)
self.__related.append(newPage)
self.__crawled[url] = newPage
else:
self.__related.append(self.__crawled[url])
def crawlRelated(self):
for link in self.__relatedURLs:
self.crawl(link)
I save it like such:
with open('medTwiceGraph.dat','w') as outf:
pickle.dump(root,outf)
and I load it like such:
def loadGraph(filename): #returns root
with open(filename,'r') as inf:
return pickle.load(inf)
root = loadGraph('medTwiceGraph.dat')
All the data loads except for the class variable __crawled.
What am I doing wrong?
Python doesn't really pickle class objects. It simply saves their names and where to find them. From the documentation of pickle
:
Similarly, classes are pickled by named reference, so the same restrictions in the unpickling environment apply. Note that none of the class’s code or data is pickled, so in the following example the class attribute
attr
is not restored in the unpickling environment:class Foo: attr = 'a class attr' picklestring = pickle.dumps(Foo)
These restrictions are why picklable functions and classes must be defined in the top level of a module.
Similarly, when class instances are pickled, their class’s code and data are not pickled along with them. Only the instance data are pickled. This is done on purpose, so you can fix bugs in a class or add methods to the class and still load objects that were created with an earlier version of the class. If you plan to have long-lived objects that will see many versions of a class, it may be worthwhile to put a version number in the objects so that suitable conversions can be made by the class’s
__setstate__()
method.
In your example you could fix your problems changing __crawled
to be an instance attribute or a global variable.
By default pickle will only use the contents of self.__dict__
and not use self.__class__.__dict__
which is what you think you want.
I say, "what you think you want" because unpickling an instance should not mutate class level sate.
If you want to change this behavior then look at __getstate__
and __setstate__
in the docs
For anyone interested, what I did was make a superclass Graph which contained an instance variable __crawled and moved my crawling functions into Graph. Page now only contains attributes describing the page and its related pages. I pickle my instance of Graph which contains all my instances of Page. Here is my code.
from urllib import urlopen
#from bs4 import BeautifulSoup
import re
import pickle
###################CLASS GRAPH####################
class Graph(object):
def __init__(self,roots = [],crawled = {}):
self.__roots = roots
self.__crawled = crawled
@property
def roots(self):
return self.__roots
@property
def crawled(self):
return self.__crawled
def crawl(self,page,url):
if url not in self.__crawled:
webpage = urlopen(url).read()
patFinderTitle = re.compile('<title>(.*)</title>')
patFinderLink = re.compile('<link rel="canonical" href="([^"]*)" />')
patFinderRelated = re.compile('<li><a href="([^"]*)"')
findPatTitle = re.findall(patFinderTitle, webpage)
findPatLink = re.findall(patFinderLink, webpage)
findPatRelated = re.findall(patFinderRelated, webpage)
newPage = Page(findPatTitle,findPatLink,findPatRelated)
page.related.append(newPage)
self.__crawled[url] = newPage
else:
page.related.append(self.__crawled[url])
def crawlRelated(self,page):
for link in page.relatedURLs:
self.crawl(page,link)
def crawlAll(self,obj,limit = 2,i = 0):
print 'number of crawled pages:', len(self.crawled)
i += 1
if i > limit:
return
else:
for rel in obj.related:
print 'crawling', rel.title
self.crawlRelated(rel)
for rel2 in obj.related:
self.crawlAll(rel2,limit,i)
def loadGraph(self,filename):
with open(filename,'r') as inf:
return pickle.load(inf)
def saveGraph(self,obj,filename):
with open(filename,'w') as outf:
pickle.dump(obj,outf)
###################CLASS PAGE#####################
class Page(Graph):
def __init__(self, title = '', link = '', relatedURLs = []):
self.__title = title
self.__link = link
self.__relatedURLs = relatedURLs
self.__related = []
@property
def relatedURLs(self):
return self.__relatedURLs
@property
def title(self):
return self.__title
@property
def related(self):
return self.__related
####################### MAIN ######################
def main(seed):
print 'doing some work...'
webpage = urlopen(seed).read()
patFinderTitle = re.compile('<title>(.*)</title>')
patFinderLink = re.compile('<link rel="canonical" href="([^"]*)" />')
patFinderRelated = re.compile('<li><a href="([^"]*)"')
findPatTitle = re.findall(patFinderTitle, webpage)
findPatLink = re.findall(patFinderLink, webpage)
findPatRelated = re.findall(patFinderRelated, webpage)
print 'found the webpage', findPatTitle
#root = Page(findPatTitle,findPatLink,findPatRelated)
G = Graph([Page(findPatTitle,findPatLink,findPatRelated)])
print 'crawling related...'
G.crawlRelated(G.roots[0])
G.crawlAll(G.roots[0])
print 'now saving...'
G.saveGraph(G, 'medTwiceGraph.dat')
print 'done'
return G
#####################END MAIN######################
#'http://medtwice.com/am-i-pregnant/'
#'medTwiceGraph.dat'
#G = main('http://medtwice.com/menopause-overview/')
#print G.crawled
def loadGraph(filename):
with open(filename,'r') as inf:
return pickle.load(inf)
G = loadGraph('MedTwiceGraph.dat')
print G.roots[0].title
print G.roots[0].related
print G.crawled
for key in G.crawled:
print G.crawled[key].title
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With