def process_contributor(self, contributor):
if self._skip_revision:
return
if contributor is None:
self._skip_revision = True
sender_tag = contributor.find(self.tag["username"])
if sender_tag is None:
try:
self._sender = contributor.find(self.tag["ip"]).text
if self._sender is None:
self._skip_revision = True
self.counter_deleted += 1
except AttributeError:
## user deleted
self._skip_revision = True
self.counter_deleted += 1
else:
try:
self._sender = mwlib.normalize_pagename(sender_tag.text)
except AttributeError:
## if username is defined but empty, look for id tag
try:
self._sender = contributor.find(self.tag["id"]).text
except KeyError:
self._skip_revision = True
def process_contributor(self, contributor):
if self._skip_revision: return
if contributor is None:
logging.warning('contributor is None')
self._skip_revision = True
sender_tag = contributor.find(self.tag['username'])
if sender_tag is None:
self._skip_revision = True
else:
try:
self._sender = mwlib.normalize_pagename(sender_tag.text)
except AttributeError:
## if username is defined but empty, look for id tag
self._sender = contributor.find(self.tag['id']).text
def process_text(self, elem):
assert self.user, "User still not defined"
text = elem.text
if not (text and self.user):
return
if (mwlib.isHardRedirect(text) or mwlib.isSoftRedirect(text)):
return
talks = self.sig_finder.find(text)
self.ecache.add(mwlib.normalize_pagename(self.user), talks)
self.count += 1
if not self.count % 500:
print self.count
def process_contributor(self, contributor):
if self._skip_revision: return
if contributor is None:
logging.warning('contributor is None')
self._skip_revision = True
sender_tag = contributor.find(self.tag['username'])
if sender_tag is None:
self._skip_revision = True
else:
try:
self._sender = mwlib.normalize_pagename(sender_tag.text)
except AttributeError:
## if username is defined but empty, look for id tag
self._sender = contributor.find(self.tag['id']).text
def process_title(self, elem):
if self._skip_revision: return
title = elem.text
a_title = title.split(':')
if len(a_title) > 1 and a_title[0] in self.user_talk_names:
self._receiver = mwlib.normalize_pagename(a_title[1])
else:
self._skip = True
return
try:
title.index('/')
self.count_archive += 1
self._skip = True
except ValueError:
pass
def process_title(self, elem):
if self._skip_revision: return
title = elem.text
a_title = title.split(':')
if len(a_title) > 1 and a_title[0] in self.user_talk_names:
self._receiver = mwlib.normalize_pagename(a_title[1])
else:
self._skip = True
return
try:
title.index('/')
self.count_archive += 1
self._skip = True
except ValueError:
pass
def process_text(self, elem):
assert self.user, "User still not defined"
text = elem.text
if not (text and self.user):
return
if (mwlib.isHardRedirect(text) or mwlib.isSoftRedirect(text)):
return
try:
talks = self.sig_finder.find(text)
self.ecache.add(mwlib.normalize_pagename(self.user), talks)
# Checks if self.user is a valid pagename
except AttributeError:
self._skip = True
return
self.count += 1
if not self.count % 500:
logging.info("Counter: %d", self.count)
def process_title(self, elem):
self.delattr(("_counter", "_type", "_title", "_skip", "_date", "_receiver"))
if self._skip_revision:
return
title = elem.text
a_title = title.split(":")
if len(a_title) > 1 and smart_str(a_title[0]) in self.user_talk_names:
self._receiver = mwlib.normalize_pagename(a_title[1])
else:
self._skip = True
return
try:
title.index("/")
self.count_archive += 1
self._skip = True
except ValueError:
pass
finally:
del title, a_title
def process_title(self, elem):
self.delattr(("_counter", "_type", "_title", "_skip", "_date",
"_receiver", "_time", "_id", "_username", "_ip"))
if self._skip_revision:
return
title = elem.text
a_title = title.split(':')
if len(a_title) > 1 and smart_str(a_title[0]) in self.user_talk_names:
self._receiver = mwlib.normalize_pagename(a_title[1])
else:
self._skip = True
return
try:
title.index('/')
self.count_archive += 1
self._skip = True
except ValueError:
pass
finally:
del title, a_title
