Pywikipedia-svn August 2009

pywikipedia-svn@lists.wikimedia.org

11 participants
93 discussions

SVN: [7174] trunk/pywikipedia/flickrripper.py
by alexsh＠svn.wikimedia.org 26 Aug '09

26 Aug '09

Revision: 7174 Author: alexsh Date: 2009-08-26 03:15:47 +0000 (Wed, 26 Aug 2009) Log Message: ----------- syntax typo Modified Paths: -------------- trunk/pywikipedia/flickrripper.py Modified: trunk/pywikipedia/flickrripper.py =================================================================== --- trunk/pywikipedia/flickrripper.py 2009-08-25 19:09:02 UTC (rev 7173) +++ trunk/pywikipedia/flickrripper.py 2009-08-26 03:15:47 UTC (rev 7174) @@ -67,7 +67,8 @@ ''' result = [] for tag in photoInfo.find('photo').find('tags').findall('tag'): - result.append(tag.text.lower()) + result.append(tag.text.lower()) + return result def getFlinfoDescription(photo_id=0): @@ -88,9 +89,9 @@ username = photoInfo.find('photo').find('owner').attrib['username'] title = photoInfo.find('photo').find('title').text if title: - title = cleanUpTitle(title) + title = cleanUpTitle(title) else: - title = u'' + title = u'' return u'Flickr - %s - %s.jpg' % (username, title) @@ -123,7 +124,7 @@ url = '' # The assumption is that the largest image is last for size in photoSizes.find('sizes').findall('size'): - url = size.attrib['source'] + url = size.attrib['source'] return url def buildDescription(flinfoDescription=u'', flickrreview=False, reviewer=u'', override=u''): @@ -181,7 +182,7 @@ print photo_id (photoInfo, photoSizes) = getPhoto(flickr=flickr, photo_id=photo_id) if (isAllowedLicense(photoInfo=photoInfo) or override): - # Tags not needed atm + # Tags not needed atm #tags=getTags(photoInfo=photoInfo) flinfoDescription = getFlinfoDescription(photo_id=photo_id) @@ -190,10 +191,10 @@ #print filename photoUrl = getPhotoUrl(photoSizes=photoSizes) #print photoUrl - photoDescription = buildDescription(flinfoDescription=flinfoDescription, flickrreview=flickrreview, reviewer=reviewer, override=override) - #wikipedia.output(photoDescription) - (newPhotoDescription, newFilename, skip)=Tkdialog(photoDescription, photoUrl, filename).run() - #wikipedia.output(newPhotoDescription) + photoDescription = buildDescription(flinfoDescription=flinfoDescription, flickrreview=flickrreview, reviewer=reviewer, override=override) + #wikipedia.output(photoDescription) + (newPhotoDescription, newFilename, skip)=Tkdialog(photoDescription, photoUrl, filename).run() + #wikipedia.output(newPhotoDescription) #if (wikipedia.Page(title=u'File:'+ filename, site=wikipedia.getSite()).exists()): # I should probably check if the hash is the same and if not upload it under a different name #wikipedia.output(u'File:' + filename + u' already exists!') @@ -202,8 +203,8 @@ #Would be nice to check before I upload if the file is already at Commons #Not that important for this program, but maybe for derived programs if not skip: - bot = upload.UploadRobot(url=photoUrl, description=newPhotoDescription, useFilename=newFilename, keepFilename=True, verifyDescription=False) - bot.upload_image(debug=False) + bot = upload.UploadRobot(url=photoUrl, description=newPhotoDescription, useFilename=newFilename, keepFilename=True, verifyDescription=False) + bot.upload_image(debug=False) return 0 class Tkdialog:

1 0

SVN: [7173] trunk/pywikipedia/reflinks.py
by nicdumz＠svn.wikimedia.org 25 Aug '09

25 Aug '09

Revision: 7173 Author: nicdumz Date: 2009-08-25 19:09:02 +0000 (Tue, 25 Aug 2009) Log Message: ----------- change MarcoBot Name in summary too. Modified Paths: -------------- trunk/pywikipedia/reflinks.py Modified: trunk/pywikipedia/reflinks.py =================================================================== --- trunk/pywikipedia/reflinks.py 2009-08-25 18:42:11 UTC (rev 7172) +++ trunk/pywikipedia/reflinks.py 2009-08-25 19:09:02 UTC (rev 7173) @@ -57,7 +57,7 @@ 'hu':u'Robot: Forráshivatkozások kibővítése a hivatkozott oldal címével', 'ko':u'봇: url만 있는 주석을 보강, (영문)[[:en:User:DumZiBoT/refLinks]] 참조', 'es':u'Formateando las referencias que no tuvieran títulos (FAQ : [[:en:User:DumZiBoT/refLinks]] )', - 'it':u'Bot: Sistemo note con collegamenti esterni senza titolo ([[Utente:Màrço27Bot/refLinks.py|documentazione]])', + 'it':u'Bot: Sistemo note con collegamenti esterni senza titolo ([[Utente:Marco27Bot/refLinks.py|documentazione]])', 'en':u'Bot: Converting bare references, using ref names to avoid duplicates, see [[User:DumZiBoT/refLinks|FAQ]]', }

1 0

SVN: [7172] trunk/pywikipedia/reflinks.py
by nicdumz＠svn.wikimedia.org 25 Aug '09

25 Aug '09

Revision: 7172 Author: nicdumz Date: 2009-08-25 18:42:11 +0000 (Tue, 25 Aug 2009) Log Message: ----------- reflinks: MarcoBot has been renamed Modified Paths: -------------- trunk/pywikipedia/reflinks.py Modified: trunk/pywikipedia/reflinks.py =================================================================== --- trunk/pywikipedia/reflinks.py 2009-08-24 17:06:26 UTC (rev 7171) +++ trunk/pywikipedia/reflinks.py 2009-08-25 18:42:11 UTC (rev 7172) @@ -45,7 +45,7 @@ stopPage = {'fr':u'Utilisateur:DumZiBoT/EditezCettePagePourMeStopper', 'de':u'Benutzer:DumZiBoT/EditThisPageToStopMe', - 'it':u'Utente:Màrço27Bot/EditThisPageToStopMe', + 'it':u'Utente:Marco27Bot/EditThisPageToStopMe', 'ko':u'사용자:GrassnBreadRefBot/EditThisPageToStopMe1', 'hu':'User:Damibot/EditThisPageToStopMe', 'en':u'User:DumZiBoT/EditThisPageToStopMe',

1 0

SVN: [7171] trunk/pywikipedia/flickrripper.py
by alexsh＠svn.wikimedia.org 24 Aug '09

24 Aug '09

Revision: 7171 Author: alexsh Date: 2009-08-24 17:06:26 +0000 (Mon, 24 Aug 2009) Log Message: ----------- typo Modified Paths: -------------- trunk/pywikipedia/flickrripper.py Modified: trunk/pywikipedia/flickrripper.py =================================================================== --- trunk/pywikipedia/flickrripper.py 2009-08-24 17:04:31 UTC (rev 7170) +++ trunk/pywikipedia/flickrripper.py 2009-08-24 17:06:26 UTC (rev 7171) @@ -55,11 +55,11 @@ ''' license = photoInfo.find('photo').attrib['license'] if (license=='4' or license=='5'): - #Is cc-by or cc-by-sa - return True + #Is cc-by or cc-by-sa + return True else: - #We don't accept other licenses - return False + #We don't accept other licenses + return False def getTags(photoInfo=None): '''

1 0

SVN: [7170] trunk/pywikipedia/flickrripper.py
by alexsh＠svn.wikimedia.org 24 Aug '09

24 Aug '09

Revision: 7170 Author: alexsh Date: 2009-08-24 17:04:31 +0000 (Mon, 24 Aug 2009) Log Message: ----------- typo Modified Paths: -------------- trunk/pywikipedia/flickrripper.py Modified: trunk/pywikipedia/flickrripper.py =================================================================== --- trunk/pywikipedia/flickrripper.py 2009-08-23 16:13:23 UTC (rev 7169) +++ trunk/pywikipedia/flickrripper.py 2009-08-24 17:04:31 UTC (rev 7170) @@ -55,11 +55,11 @@ ''' license = photoInfo.find('photo').attrib['license'] if (license=='4' or license=='5'): - #Is cc-by or cc-by-sa - return True + #Is cc-by or cc-by-sa + return True else: - #We don't accept other licenses - return False + #We don't accept other licenses + return False def getTags(photoInfo=None): ''' @@ -67,7 +67,7 @@ ''' result = [] for tag in photoInfo.find('photo').find('tags').findall('tag'): - result.append(tag.text.lower()) + result.append(tag.text.lower()) return result def getFlinfoDescription(photo_id=0): @@ -88,9 +88,9 @@ username = photoInfo.find('photo').find('owner').attrib['username'] title = photoInfo.find('photo').find('title').text if title: - title = cleanUpTitle(title) + title = cleanUpTitle(title) else: - title = u'' + title = u'' return u'Flickr - %s - %s.jpg' % (username, title) @@ -123,7 +123,7 @@ url = '' # The assumption is that the largest image is last for size in photoSizes.find('sizes').findall('size'): - url = size.attrib['source'] + url = size.attrib['source'] return url def buildDescription(flinfoDescription=u'', flickrreview=False, reviewer=u'', override=u''): @@ -180,28 +180,28 @@ if(photo_id): print photo_id (photoInfo, photoSizes) = getPhoto(flickr=flickr, photo_id=photo_id) - if (isAllowedLicense(photoInfo=photoInfo) or override): + if (isAllowedLicense(photoInfo=photoInfo) or override): # Tags not needed atm - #tags=getTags(photoInfo=photoInfo) + #tags=getTags(photoInfo=photoInfo) - flinfoDescription = getFlinfoDescription(photo_id=photo_id) + flinfoDescription = getFlinfoDescription(photo_id=photo_id) - filename = getFilename(photoInfo=photoInfo) - #print filename - photoUrl = getPhotoUrl(photoSizes=photoSizes) - #print photoUrl + filename = getFilename(photoInfo=photoInfo) + #print filename + photoUrl = getPhotoUrl(photoSizes=photoSizes) + #print photoUrl photoDescription = buildDescription(flinfoDescription=flinfoDescription, flickrreview=flickrreview, reviewer=reviewer, override=override) #wikipedia.output(photoDescription) (newPhotoDescription, newFilename, skip)=Tkdialog(photoDescription, photoUrl, filename).run() #wikipedia.output(newPhotoDescription) - #if (wikipedia.Page(title=u'File:'+ filename, site=wikipedia.getSite()).exists()): - # I should probably check if the hash is the same and if not upload it under a different name - #wikipedia.output(u'File:' + filename + u' already exists!') - #else: - #Do the actual upload - #Would be nice to check before I upload if the file is already at Commons - #Not that important for this program, but maybe for derived programs - if not skip: + #if (wikipedia.Page(title=u'File:'+ filename, site=wikipedia.getSite()).exists()): + # I should probably check if the hash is the same and if not upload it under a different name + #wikipedia.output(u'File:' + filename + u' already exists!') + #else: + #Do the actual upload + #Would be nice to check before I upload if the file is already at Commons + #Not that important for this program, but maybe for derived programs + if not skip: bot = upload.UploadRobot(url=photoUrl, description=newPhotoDescription, useFilename=newFilename, keepFilename=True, verifyDescription=False) bot.upload_image(debug=False) return 0 @@ -326,12 +326,12 @@ flickrreview = False # Set the Flickr reviewer - if(config.flickr['reviewer']): + if config.flickr['reviewer']: reviewer = config.flickr['reviewer'] - elif(config.sysopnames['commons']['commons']): + elif config.sysopnames['commons']['commons']: reviewer = config.sysopnames['commons']['commons'] - elif(config.usernames['Commons']['Commons']): - reviewer = config.usernames['Commons']['Commons'] + elif config.usernames['commons']['commons']: + reviewer = config.usernames['commons']['commons'] else: reviewer = u''

1 0

SVN: [7169] trunk/pywikipedia/flickrripper.py
by multichill＠svn.wikimedia.org 23 Aug '09

23 Aug '09

Revision: 7169 Author: multichill Date: 2009-08-23 16:13:23 +0000 (Sun, 23 Aug 2009) Log Message: ----------- First version of flickrripper. It works, but I still have to do a lot to get a nice program. Added Paths: ----------- trunk/pywikipedia/flickrripper.py Added: trunk/pywikipedia/flickrripper.py =================================================================== --- trunk/pywikipedia/flickrripper.py (rev 0) +++ trunk/pywikipedia/flickrripper.py 2009-08-23 16:13:23 UTC (rev 7169) @@ -0,0 +1,389 @@ +#!/usr/bin/python +# -*- coding: utf-8 -*- +''' +Tool to copy a flickr stream to Commons + +# Get a set to work on (start with just a username). +# * Make it possible to delimit the set (from/to) +#For each image +#*Check the license +#*Check if it isn't already on Commons +#*Build suggested filename +#**Check for name collision and maybe alter it +#*Pull description from Flinfo +#*Show image and description to user +#**Add a nice hotcat lookalike for the adding of categories +#**Filter the categories +#*Upload the image + +Todo: +*Check if the image is already uploaded (SHA hash) +*Check and prevent filename collisions +**Initial suggestion +**User input +*Filter the categories + +''' +# +# (C) Multichill, 2009 +# +# Distributed under the terms of the MIT license. +# +__version__ = '$Id: upload_to_commons.py 69 2009-08-23 11:44:26Z multichill $' + +import sys, urllib, re, StringIO +import wikipedia, config, query, imagerecat, upload + +import flickrapi +import xml.etree.ElementTree +from Tkinter import * +from PIL import Image, ImageTk + +def getPhoto(flickr=None, photo_id=''): + ''' + Get the photo info and the photo sizes so we can use these later on + ''' + photoInfo = flickr.photos_getInfo(photo_id=photo_id) + #xml.etree.ElementTree.dump(photoInfo) + photoSizes = flickr.photos_getSizes(photo_id=photo_id) + #xml.etree.ElementTree.dump(photoSizes) + return (photoInfo, photoSizes) + +def isAllowedLicense(photoInfo=None): + ''' + Check if the image contains the right license + ''' + license = photoInfo.find('photo').attrib['license'] + if (license=='4' or license=='5'): + #Is cc-by or cc-by-sa + return True + else: + #We don't accept other licenses + return False + +def getTags(photoInfo=None): + ''' + Get all the tags on a photo + ''' + result = [] + for tag in photoInfo.find('photo').find('tags').findall('tag'): + result.append(tag.text.lower()) + return result + +def getFlinfoDescription(photo_id=0): + ''' + Get the description from http://wikipedia.ramselehof.de/flinfo.php + ''' + parameters = urllib.urlencode({'id' : photo_id, 'raw' : 'on'}) + + #print 'Flinfo gaat nu aan de slag' + rawDescription = urllib.urlopen("http://wikipedia.ramselehof.de/flinfo.php?%s" % parameters).read() + #print rawDescription.decode('utf-8') + return rawDescription.decode('utf-8') + +def getFilename(photoInfo=None): + ''' + Build a good filename for the upload based on the username and the title + ''' + username = photoInfo.find('photo').find('owner').attrib['username'] + title = photoInfo.find('photo').find('title').text + if title: + title = cleanUpTitle(title) + else: + title = u'' + + return u'Flickr - %s - %s.jpg' % (username, title) + +def cleanUpTitle(title): + title = title.strip() + + title = re.sub("[<{\\[]", "(", title) + title = re.sub("[>}\\]]", ")", title) + title = re.sub("[ _]?\$!\$", "", title) + title = re.sub(",:[ _]", ", ", title) + title = re.sub("[;:][ _]", ", ", title) + title = re.sub("[\t\n ]+", " ", title) + title = re.sub("[\r\n ]+", " ", title) + title = re.sub("[\n]+", "", title) + title = re.sub("[?!]([.\"]|$)", "\\1", title) + title = re.sub("[&#%?!]", "^", title) + title = re.sub("[;]", ",", title) + title = re.sub("[/+\\\\:]", "-", title) + title = re.sub("--+", "-", title) + title = re.sub(",,+", ",", title) + title = re.sub("[-,^]([.]|$)", "\\1", title) + title = title.replace(" ", "_") + + return title + +def getPhotoUrl(photoSizes=None): + ''' + Get the url of the jpg file with the highest resolution + ''' + url = '' + # The assumption is that the largest image is last + for size in photoSizes.find('sizes').findall('size'): + url = size.attrib['source'] + return url + +def buildDescription(flinfoDescription=u'', flickrreview=False, reviewer=u'', override=u''): + ''' + Build the final description for the image. The description is based on the info from flickrinfo and improved. + ''' + description = flinfoDescription + + if(override): + description = description.replace(u'{{cc-by-sa-2.0}}\n', u'') + description = description.replace(u'{{cc-by-2.0}}\n', u'') + description = description.replace(u'{{flickrreview}}\n', u'') + description = description.replace(u'{{copyvio|Flickr, licensed as "All Rights Reserved" which is not a free license --~~~~}}\n', u'') + description = description.replace(u'=={{int:license}}==', u'=={{int:license}}==\n' + override) + elif(flickrreview): + if(reviewer): + description = description.replace(u'{{flickrreview}}', u'{{flickrreview|' + reviewer + '|{{subst:CURRENTYEAR}}-{{subst:CURRENTMONTH}}-{{subst:CURRENTDAY2}}}}') + description = description.replace(u'\r\n', u'\n') + return description + +def getPhotos(flickr=None, user_id=u'', group_id=u'', photoset_id=u'', tags=u''): + result = [] + # http://www.flickr.com/services/api/flickr.groups.pools.getPhotos.html + if(group_id): + #First get the total number of photo's in the group + photos = flickr.groups_pools_getPhotos(group_id=group_id, user_id=user_id, tags=tags, per_page='100', page='1') + pages = photos.find('photos').attrib['pages'] + + for i in range(1, int(pages)): + for photo in flickr.groups_pools_getPhotos(group_id=group_id, user_id=user_id, tags=tags, per_page='100', page=i).find('photos').getchildren(): + yield photo.attrib['id'] + + # http://www.flickr.com/services/api/flickr.photosets.getPhotos.html + elif(photoset_id): + photos = flickr.photosets_getPhotos(photoset_id=photoset_id, per_page='100', page='1') + pages = photos.find('photos').attrib['pages'] + + for i in range(1, int(pages)): + for photo in flickr.photosets_getPhotos(photoset_id=photoset_id, per_page='100', page=i).find('photos').getchildren(): + yield photo.attrib['id'] + + # http://www.flickr.com/services/api/flickr.people.getPublicPhotos.html + elif(user_id): + photos = flickr.people_getPublicPhotos(user_id=user_id, per_page='100', page='1') + pages = photos.find('photos').attrib['pages'] + + for i in range(1, int(pages)): + for photo in flickr.people_getPublicPhotos(user_id=user_id, per_page='100', page=i).find('photos').getchildren(): + yield photo.attrib['id'] + return + + +def processPhoto(flickr=None, photo_id=u'', flickrreview=False, reviewer=u'', override=u''): + if(photo_id): + print photo_id + (photoInfo, photoSizes) = getPhoto(flickr=flickr, photo_id=photo_id) + if (isAllowedLicense(photoInfo=photoInfo) or override): + # Tags not needed atm + #tags=getTags(photoInfo=photoInfo) + + flinfoDescription = getFlinfoDescription(photo_id=photo_id) + + filename = getFilename(photoInfo=photoInfo) + #print filename + photoUrl = getPhotoUrl(photoSizes=photoSizes) + #print photoUrl + photoDescription = buildDescription(flinfoDescription=flinfoDescription, flickrreview=flickrreview, reviewer=reviewer, override=override) + #wikipedia.output(photoDescription) + (newPhotoDescription, newFilename, skip)=Tkdialog(photoDescription, photoUrl, filename).run() + #wikipedia.output(newPhotoDescription) + #if (wikipedia.Page(title=u'File:'+ filename, site=wikipedia.getSite()).exists()): + # I should probably check if the hash is the same and if not upload it under a different name + #wikipedia.output(u'File:' + filename + u' already exists!') + #else: + #Do the actual upload + #Would be nice to check before I upload if the file is already at Commons + #Not that important for this program, but maybe for derived programs + if not skip: + bot = upload.UploadRobot(url=photoUrl, description=newPhotoDescription, useFilename=newFilename, keepFilename=True, verifyDescription=False) + bot.upload_image(debug=False) + return 0 + +class Tkdialog: + def __init__(self, photoDescription, photoUrl, filename): + self.root=Tk() + #"%dx%d%+d%+d" % (width, height, xoffset, yoffset) + self.root.geometry("1600x1000+10-10") + + self.root.title(filename) + self.photoDescription = photoDescription + self.filename = filename + self.photoUrl = photoUrl + self.skip=False + self.exit=False + + ## Init of the widgets + # The image + self.image=self.getImage(self.photoUrl, 800, 600) + self.imagePanel=Label(self.root, image=self.image) + + self.imagePanel.image = self.image + + # The filename + self.filenameLabel=Label(self.root,text=u"Suggested filename") + self.filenameField=Entry(self.root, width=100) + self.filenameField.insert(END, filename) + + # The description + self.descriptionLabel=Label(self.root,text=u"Suggested description") + self.descriptionScrollbar=Scrollbar(self.root, orient=VERTICAL) + self.descriptionField=Text(self.root) + self.descriptionField.insert(END, photoDescription) + self.descriptionField.config(state=NORMAL, height=12, width=100, padx=0, pady=0, wrap=WORD, yscrollcommand=self.descriptionScrollbar.set) + self.descriptionScrollbar.config(command=self.descriptionField.yview) + + # The buttons + self.okButton=Button(self.root, text="OK", command=self.okFile) + self.skipButton=Button(self.root, text="Skip", command=self.skipFile) + + ## Start grid + # The image + self.imagePanel.grid(row=0, column=0, rowspan=11, columnspan=4) + + # The filename + self.filenameLabel.grid(row=11, column=0) + self.filenameField.grid(row=11, column=1, columnspan=3) + + # The description + self.descriptionLabel.grid(row=12, column=0) + self.descriptionField.grid(row=12, column=1, columnspan=3) + self.descriptionScrollbar.grid(row=12, column=5) + + # The buttons + self.okButton.grid(row=13, column=1, rowspan=2) + self.skipButton.grid(row=13, column=2, rowspan=2) + + def getImage(self, url, width, height): + image=urllib.urlopen(url).read() + output = StringIO.StringIO(image) + image2 = Image.open(output) + image2.thumbnail((width, height)) + imageTk = ImageTk.PhotoImage(image2) + return imageTk + + def okFile(self): + ''' + The user pressed the OK button. + ''' + self.filename=self.filenameField.get() + self.photoDescription=self.descriptionField.get(0.0, END) + self.root.destroy() + + def skipFile(self): + ''' + The user pressed the Skip button. + ''' + self.skip=True + self.root.destroy() + + def run(self): + ''' + Activate the dialog and return the new name and if the image is skipped. + ''' + self.root.mainloop() + return (self.photoDescription, self.filename, self.skip) + + +def usage(): + wikipedia.output(u"Flickrripper is a tool to transfer flickr photos to Wikimedia Commons") + wikipedia.output(u"-group_id:<group_id>\n") + wikipedia.output(u"-photoset_id:<photoset_id>\n") + wikipedia.output(u"-user_id:<user_id>\n") + wikipedia.output(u"-tags:<tag>\n") + return + +def main(): + site = wikipedia.getSite(u'commons', u'commons') + wikipedia.setSite(site) + #imagerecat.initLists() + + #Get the api key + if(config.flickr['api_key']): + flickr = flickrapi.FlickrAPI(config.flickr['api_key']) + else: + wikipedia.output('Flickr api key not found! Get yourself an api key') + wikipedia.output('Any flickr user can get a key at http://www.flickr.com/services/api/keys/apply/') + return + + group_id = u'' + photoset_id = u'' + user_id = u'' + tags = u'' + totalPhotos = 0 + uploadedPhotos = 0 + + # Do we mark the images as reviewed right away? + if(config.flickr['review']): + flickrreview = config.flickr['review'] + else: + flickrreview = False + + # Set the Flickr reviewer + if(config.flickr['reviewer']): + reviewer = config.flickr['reviewer'] + elif(config.sysopnames['commons']['commons']): + reviewer = config.sysopnames['commons']['commons'] + elif(config.usernames['Commons']['Commons']): + reviewer = config.usernames['Commons']['Commons'] + else: + reviewer = u'' + + override = u'' + + for arg in wikipedia.handleArgs(): + if arg.startswith('-group_id'): + if len(arg) == 9: + group_id = wikipedia.input(u'What is the group_id of the pool?') + else: + group_id = arg[10:] + elif arg.startswith('-photoset_id'): + if len(arg) == 12: + photoset_id = wikipedia.input(u'What is the photoset_id)?') + else: + photoset_id = arg[13:] + elif arg.startswith('-user_id'): + if len(arg) == 8: + user_id = wikipedia.input(u'What is the user_id of the flickr user?') + else: + user_id = arg[9:] + elif arg.startswith('-tags'): + if len(arg) == 5: + tags = wikipedia.input(u'What is the tag you want to filter out (currently only one supported)?') + else: + tags = arg[6:] + elif arg == '-flickrreview': + flickrreview = True + elif arg.startswith('-reviewer'): + if len(arg) == 9: + reviewer = wikipedia.input(u'Who is the reviewer?') + else: + reviewer = arg[10:] + elif arg.startswith('-override'): + if len(arg) == 9: + override = wikipedia.input(u'What is the override text?') + else: + override = arg[10:] + + if(user_id or group_id or photoset_id): + for photo_id in getPhotos(flickr=flickr, user_id=user_id, group_id=group_id, photoset_id=photoset_id, tags=tags): + uploadedPhotos = uploadedPhotos + processPhoto(flickr=flickr, photo_id=photo_id, flickrreview=flickrreview, reviewer=reviewer, override=override) + totalPhotos = totalPhotos + 1 + else: + usage() + + wikipedia.output(u'Finished running') + wikipedia.output(u'Total photos: ' + str(totalPhotos)) + wikipedia.output(u'Uploaded photos: ' + str(uploadedPhotos)) + +if __name__ == "__main__": + try: + main() + finally: + wikipedia.stopme()

1 0

SVN: [7168] trunk/pywikipedia/imageuncat.py
by multichill＠svn.wikimedia.org 23 Aug '09

23 Aug '09

Revision: 7168 Author: multichill Date: 2009-08-23 11:33:19 +0000 (Sun, 23 Aug 2009) Log Message: ----------- Add 1 template and remove 1 template Modified Paths: -------------- trunk/pywikipedia/imageuncat.py Modified: trunk/pywikipedia/imageuncat.py =================================================================== --- trunk/pywikipedia/imageuncat.py 2009-08-21 18:05:58 UTC (rev 7167) +++ trunk/pywikipedia/imageuncat.py 2009-08-23 11:33:19 UTC (rev 7168) @@ -85,7 +85,6 @@ u'Ay', u'Az', u'Ba', - u'Bad name', u'BadJPEG', u'Bar', u'BArch-License', @@ -453,6 +452,7 @@ u'Iu', u'Ja', u'Ja2', + u'James K. Lindsey permission', u'Jbo', u'Jean-PolGRANDMONTCredit', u'JewishEncyclopedia',

1 0

SVN: [7167] branches/rewrite/pywikibot/pagegenerators.py
by russblau＠svn.wikimedia.org 21 Aug '09

21 Aug '09

Revision: 7167 Author: russblau Date: 2009-08-21 18:05:58 +0000 (Fri, 21 Aug 2009) Log Message: ----------- Add command-line support for 'step' and 'limit' parameters of page generators. Modified Paths: -------------- branches/rewrite/pywikibot/pagegenerators.py Modified: branches/rewrite/pywikibot/pagegenerators.py =================================================================== --- branches/rewrite/pywikibot/pagegenerators.py 2009-08-20 22:37:32 UTC (rev 7166) +++ branches/rewrite/pywikibot/pagegenerators.py 2009-08-21 18:05:58 UTC (rev 7167) @@ -91,6 +91,9 @@ pages on several wiki sites, this is not well tested, so check your edits! +-limit:n When used with any other argument that specifies a set + of pages, work on no more than n pages in total + -links Work on all pages that are linked from a certain page. Argument can also be given as "-links:linkingpagetitle". @@ -118,6 +121,10 @@ -regex Obsolete, use -titleregex +-step:n When used with any other argument that specifies a set + of pages, only retrieve n pages at a time from the wiki + server + -titleregex Work on titles that match the given regular expression. -transcludes Work on all pages that use a certain template. @@ -155,6 +162,8 @@ def __init__(self): self.gens = [] self.namespaces = [] + self.step = None + self.limit = None def getCombinedGenerator(self): """Return the combination of all accumulated generators. @@ -162,14 +171,21 @@ Only call this after all arguments have been parsed. """ - if self.namespaces: - namespaces = [int(n) for n in self.namespaces] - for i in xrange(len(self.gens)): - if isinstance(self.gens[i], pywikibot.data.api.QueryGenerator): + namespaces = [int(n) for n in self.namespaces] + for i in xrange(len(self.gens)): + if isinstance(self.gens[i], pywikibot.data.api.QueryGenerator): + if self.namespaces: self.gens[i].set_namespace(namespaces) - else: + if self.step: + self.gens[i].set_query_increment(self.step) + if self.limit: + self.gens[i].set_maximum_items(self.limit) + else: + if self.namespaces: self.gens[i] = NamespaceFilterPageGenerator( self.gens[i], namespaces) + if self.limit: + self.gens[i] = itertools.islice(self.gens[i], self.limit) if len(self.gens) == 0: return None elif len(self.gens) == 1: @@ -282,6 +298,18 @@ else: self.namespaces.extend(arg[len('-ns:'):].split(",")) return True + elif arg.startswith('-step'): + if len(arg) == len('-step'): + self.step = int(pywikibot.input("What is the step value?")) + else: + self.step = int(arg[len('-step:'):]) + return True + elif arg.startswith('-limit'): + if len(arg) == len('-limit'): + self.limit = int(pywikibot.input("What is the limit value?")) + else: + self.limit = int(arg[len('-limit:'):]) + return True elif arg.startswith('-catr'): gen = self.getCategoryGen(arg, len("-catr"), recurse = True) elif arg.startswith('-category'):

1 0

SVN: [7166] trunk/pywikipedia/families/omegawiki_family.py
by siebrand＠svn.wikimedia.org 21 Aug '09

21 Aug '09

Revision: 7166 Author: siebrand Date: 2009-08-20 22:37:32 +0000 (Thu, 20 Aug 2009) Log Message: ----------- Update omegawiki_family.py Modified Paths: -------------- trunk/pywikipedia/families/omegawiki_family.py Modified: trunk/pywikipedia/families/omegawiki_family.py =================================================================== --- trunk/pywikipedia/families/omegawiki_family.py 2009-08-20 20:53:10 UTC (rev 7165) +++ trunk/pywikipedia/families/omegawiki_family.py 2009-08-20 22:37:32 UTC (rev 7166) @@ -14,10 +14,10 @@ self.langs['omegawiki'] = 'www.omegawiki.org' self.namespaces[4] = { - '_default': [u'OmegaWiki'], + '_default': [u'Meta'], } self.namespaces[5] = { - '_default': [u'OmegaWiki talk'], + '_default': [u'Meta talk'], } self.namespaces[6] = { '_default': [u'File'], @@ -31,18 +31,6 @@ self.namespaces[17] = { '_default': [u'Expression talk'], } - self.namespaces[18] = { - '_default': [u'Collection'], - } - self.namespaces[19] = { - '_default': [u'Collection talk'], - } - self.namespaces[20] = { - '_default': [u'Relation'], - } - self.namespaces[21] = { - '_default': [u'Relation talk'], - } self.namespaces[22] = { '_default': [u'Portal'], } @@ -67,6 +55,12 @@ self.namespaces[29] = { '_default': [u'NeedsTranslationTo talk'], } + self.namespaces[30] = { + '_default': [u'Partner'], + } + self.namespaces[31] = { + '_default': [u'Partner talk'], + } # On most Wikipedias page names must start with a capital letter, but some # languages don't use this. @@ -77,7 +71,7 @@ return 'www.omegawiki.org' def version(self, code): - return "1.10alpha" + return "1.16alpha" def scriptpath(self, code): return ''

1 0

SVN: [7165] trunk/pywikipedia/commonsdelinker/image_replacer.py
by siebrand＠svn.wikimedia.org 20 Aug '09

20 Aug '09

Revision: 7165 Author: siebrand Date: 2009-08-20 20:53:10 +0000 (Thu, 20 Aug 2009) Log Message: ----------- Revert r7131 in image_replacer.py. Caused: [2009-08-20 20:46:48] Warning! Unable to read replacement log. [2009-08-20 20:46:48] UnboundLocalError: local variable 'response' referenced before assignment Modified Paths: -------------- trunk/pywikipedia/commonsdelinker/image_replacer.py Modified: trunk/pywikipedia/commonsdelinker/image_replacer.py =================================================================== --- trunk/pywikipedia/commonsdelinker/image_replacer.py 2009-08-20 20:44:49 UTC (rev 7164) +++ trunk/pywikipedia/commonsdelinker/image_replacer.py 2009-08-20 20:53:10 UTC (rev 7165) @@ -10,7 +10,7 @@ # Distributed under the terms of the MIT license. # __version__ = '$Id$' -import config, wikipedia, query +import config, wikipedia, simplejson import re, time import threadpool import sys, os, signal, traceback @@ -149,19 +149,21 @@ """ Fetch the last 50 revisions using the API """ address = self.site.api_address() - predata = { - 'action': 'query', - 'prop': 'revisions', - 'titles': title.encode('utf-8'), - 'rvprop': 'timestamp|user|comment|content', - 'rvlimit': '50', - } + predata = [ + ('action', 'query'), + ('prop', 'revisions'), + ('titles', title.encode('utf-8')), + ('rvprop', 'timestamp|user|comment|content'), + ('rvlimit', '50'), + ('format', 'json'), + ] if username: - predata['rvexcludeuser'] = username.encode('utf-8') + predata.append(('rvexcludeuser', username.encode('utf-8'))) if since: - predata['rvend'] = since - response, data = query.GetData(predata, self.site, back_response = True) - if data.has_key('error'): + predata.append(('rvend', since)) + response, data = self.site.postForm(address, predata) + data = simplejson.loads(data) + if 'error' in data: raise RuntimeError(data['error']) page = data['query']['pages'].values()[0]

1 0

← Newer
1
2
3
4
5
6
7
8
9
10
Older →

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

Pywikipedia-svn August 2009