Gebruiker:Valhallasw/imagesearch

Huidige versie

#################################
# INTERWIKI IMAGE HARVESTER
# Uses interwiki links on a page to find images used on other wikis to find useable images for subjects
#
# Uses a wiki format to output, but outputs to stdout.
#
# (C)2006 by [[nl:Gebruiker:Valhallasw]] and [[nl:Gebruiker:Gerbennn]]
# Licenced under the MIT licence
#################################


import wikipedia,config,re,sys
try:
  # loading blank lists
  images = []
  commons = []
  nocommons = []

  page = wikipedia.Page(wikipedia.getSite(), wikipedia.input("Please enter wiki page:"))

  ########
  # 1) Get a list of images
  ##############################################################################

  # get interwiki links
  links = page.interwiki()
  for link in links:
    sys.stdout.flush() # flush stdout (useful when piping to a file)
    try:
      # add the found image links to the images list
      images.extend(link.imagelinks())
    except wikipedia.IsRedirectPage,target:
      wikipedia.output(u'DBG: %s raises IsRedirectPage to %s' % (link.aslink(), target.args[0]))
      try:
        # if the page is a redirect, try using the redirect target
        link = wikipedia.Page(link.site(), target.args[0])
        images.extend(link.imagelinks())
      except (wikipedia.NoPage, wikipedia.PageNotFound, wikipedia.IsRedirectPage): #except non-fatal errors
        wikipedia.output(u'DBG: %s raised non-fatal %s exception' % (link.aslink(), sys.exc_info()[0]))

    except (wikipedia.NoPage, wikipedia.PageNotFound): #except non-fatal errors
        wikipedia.output(u'DBG: %s raised non-fatal %s exception' % (link.aslink(), sys.exc_info()[0]))

  ########
  # 2) Sort the images to commons- and site-images; Remove commons duplicates
  ##############################################################################
  for image in images:
    sys.stdout.flush()

    # try to retrieve the image from commons:
    temppage = wikipedia.Page(wikipedia.getSite('commons','commons'),'image:'+image.titleWithoutNamespace())
    if temppage.exists():
      wikipedia.output(u'Found commons image: '+temppage.aslink())
      if commons.count(temppage) == 0: #check if the page is not already in the list
        commons.append(temppage)
    else:
       wikipedia.output(u'Found image: '+image.aslink())
       nocommons.append(image)

  ########
  # 3) Output the information
  ##############################################################################

  # Output H1 caption with page title
  wikipedia.output(u'==%s==' % page.title())
  # Output table with commons images and descriptions
  wikipedia.output(u'===Commons===\n{| class="wikitable"')
  for image in commons:
    wikipedia.output(u'|-\n|[[%s|200px]] || %s' % (image.title(), re.sub('(\n|</?nowiki>)','',image.get())))
    #                       200px thumb     description in <nowiki> tags

  #output images that do not appear on commons as an unnumbered list
  wikipedia.output(u'|}\n===Non-commons===')
  for image in nocommons:
    wikipedia.output(u'* [[:%s:%s]]' % (image.site().lang, image.title()))

finally:
    wikipedia.stopme()

Oude versie(s)

Pythonscriptje om een lijst met images te genereren.

dev-uitvoering, op het moment alleen direct in python te gebruiken door te plakken ;)

import wikipedia,config,re

page = wikipedia.Page(wikipedia.getSite(),"Kwantumcomputer")
contents = page.get()
links = re.findall('\[\[..\:.*\]\]',contents)

for link in links:
	site = wikipedia.getSite(re.sub('\[\[(..)\:.*\]\]','\\1',link))
	pagename = re.sub('\[\[..\:(.*)\]\]','\\1',link)
	temppage = wikipedia.Page(site, pagename)
	temppage.imagelinks()

uiteraard kwantumcomputer door een pagina naar keuze vervangen ;)

pl:Grafika:Kane QC.png

---

Poging tot verbetering door Gerbennn

import wikipedia,config,re
try:
    page = wikipedia.Page(wikipedia.getSite(),"Computer")
    links = page.interwiki()
    for link in links:
            link.imagelinks()
finally:
    wikipedia.stopme()

---

meer van valhalla:

/*  
    Interwiki image harvester
    (C) 2006 by [[nl:Gebruiker:Valhallasw]] and [[nl:Gebruiker:Gerbennn]]
    Licenced under the MIT License
*/
import wikipedia,config,re,sys
try:
  images = []
  page = wikipedia.Page(wikipedia.getSite(),"Computer")
  links = page.interwiki()
  for link in links:

    try:
      images = images + link.imagelinks()
    except wikipedia.IsRedirectPage,target:
      wikipedia.output(u'DBG: %s raises IsRedirectPage to %s' % (link.aslink(), target.args[0]))
      try:
        link = wikipedia.Page(link.site(), target.args[0])
      except:
        wikipedia.output(u'DBG: %s raises %s' % (link.aslink(), sys.exc_info()[0]))

    except:
        wikipedia.output(u'DBG: %s raises %s' % (link.aslink(), sys.exc_info()[0]))

  out = u'{| class="wikitable" \n|'+page.aslink()+u'\n|'
  for image in images:
    temppage = wikipedia.Page(wikipedia.getSite('commons','commons'),'image:'+image.titleWithoutNamespace())
    if temppage.exists():
      wikipedia.output(u'Found commons image: '+temppage.aslink())
      out = out + '<b>[[:%s]]</b><br />' % temppage.title()
    else:
       wikipedia.output(u'Found image: '+image.aslink())
       out = out + '[[:%s:%s]]<br />' % (image.site().lang, image.title())

  out = out + u'\n|}'
  wikipedia.output(out)

finally:
    wikipedia.stopme()

geeft: