Wikipedia_scrape_img

import wikipedia
import io
import urllib.request
from PIL import Image
import time

languages = [ "aa", "ab", "ady" , "ady-cyrl" , "aeb" , "af"  ,
    "ak" , "aln" , "als" , "am"  , "an" , "ang" , "anp"  , "ar"  , "arc"  , "arn"  , "arq"  , "ary"  , "arz"  , "as"  , "ase"  , "ast"  , "atj" , "av" , "avk"  , "awa"  ,"ay"  , "az"  , "azb" ,"ba" , "ban" , "bar"  , "bat-smg" , "bbc"   "bbc-latn"  , "bcc"  ,"bcl" , "be"  , "be-tarask" , "bgn"  ,"bh"  , "bho"  , "bi" , "bjn"  , "bm" , "bn"  , "bo"  ,"bpy"  , "bqi"  , "br"  , "brh"  , "bs" ,"bto"  , "bug"  , "bxr"  , "ca" , "cbk-zam"  , "cdo" , "ce" , "ceb" ,"ch" , "cho"  , "chr"  ,"chy"  , "ckb" ,"co"  , "cps" , "cr" , "crh" ,"crh-latn"  , "cs"  , "csb"  , "cu"  , "cv"  , "cy"  , "da" , "de" , "de-at" , "de-ch"  , "de-formal" , "din" , "diq"  , "dsb"  ,"dtp" , "dty" , "dv" ,"dz" , "ee" ,"egl" ,"el"  , "eml" ,"en" , "en-ca"  , "en-gb"  ,"eo" , "es"  , "et" , "eu"  ,"ext" , "fa"  , "ff"  , "fi"  , "fit" , "fiu-vro" , "fj" , "fo" , "fr" , "frc" , "frp"  , "frr" , "fur" ,"fy"  , "ga"  , "gag" ,"gan" , "gan-hans" , "gan-hant"  , "gcr" , "gd"  ,"gl"  , "glk" , "gn"  , "gom"  , "gom-deva"  , "gom-latn" , "gor" ,"got" , "grc"  , "gsw" , "gu"  , "gv" , "ha"  , "hak"  , "haw" , "he" , "hi"  ,"hif"  , "hif-latn"  ,"hil"  , "ho" , "hr" ,"hrx" ,"hsb"  ,"ht" , "hu" , "hy" , "hz" , "ia" , "id"  , "ie" , "ig" , "ii"  ,"ik"  , "ike-cans"  ,"ike-latn"  , "ilo"  , "inh"  , "io"  , "is" , "it"  , "iu" , "ja" ,"jam" , "jbo"  , "jut"  , "jv"  ,"ka" , "kaa"  , "kab" , "kbd" , "kbd-cyrl" , "kbp"  ,"kg" , "khw"  , "ki" , "kiu" , "kj" ,"kk"  , "kk-arab" ,"kk-cn" ,"kk-cyrl" , "kk-kz"  ,"kk-latn" , "kk-tr" , "kl" , "km" ,"kn"  ,"ko" , "ko-kp" , "koi"  , "kr"  , "krc"  ,"kri" , "krj"  , "krl"  , "ks" , "ks-arab"  ,"ks-deva" , "ksh"  , "ku"  , "ku-arab"  ,"ku-latn"  ,"kum" , "kv"  , "kw"  , "ky"  , "la" ,"lad" , "lb" , "lbe" , "lez" , "lfn"  ,"lg" , "li"  ,"lij" , "liv"  , "lki" ,"lmo" ,"ln" ,"lo"  , "loz" , "lrc"  , "lt"  , "ltg" , "lus"  , "luz"  , "lv"  , "lzh" , "lzz" ,"mai"  , "map-bms"  , "mdf"  , "mg"  ,"mh"  , "mhr" ,"mi"  , "min" , "mk"  , "ml"  ,"mn"  , "mo" , "mr" ,"mrj"  , "ms"  , "mt"  , "mus" , "mwl"  ,"my" , "myv" , "mzn" , "na"  , "nah"  ,"nan" , "nap" , "nb" , "nds" ,"nds-nl" ,"ne" ,"new"  , "ng"  ,"niu"  ,"nl" , "nl-informal" , "nn" ,"no"  , "nov" ,"nrm" ,"nso" , "nv"  , "ny" ,"nys" ,"oc" ,"olo"  ,"om" ,"or" , "os"  ,"pa"  ,"pag"  , "pam"  ,"pap"  , "pcd" ,"pdc"  ,"pdt" , "pfl" , "pi"  , "pih" , "pl" , "pms" , "pnb" ,"pnt" ,"prg" , "ps" , "pt" , "pt-br" , "qu" , "qug"  ,"rgn"  , "rif" ,"rm" , "rmy" , "rn"  , "ro"  ,"roa-rup"  ,"roa-tara"  , "ru"  , "rue"  , "rup" , "ruq" , "ruq-cyrl"  , "ruq-latn" ,"rw" , "sa" , "sah" , "sat" , "sc" ,"scn"  , "sco" , "sd"  , "sdc"  , "sdh" ,"se"  ,"sei"  , "ses"  ,"sg" ,"sgs"  , "sh" ,"shi" , "shi-latn"  ,"shi-tfng" ,"shn"  , "si" , "simple" ,"sk"  ,"skr" , "skr-arab" ,"sl" , "sli" , "sm" ,"sma" ,"sn" ,"so" , "sq"  ,"sr" , "sr-ec" , "sr-el" ,"srn" ,"ss" , "st" ,"stq" , "sty" ,"su"  , "sv"  , "sw" ,"szl" , "ta" , "tay" ,"tcy", "te"  , "tet" ,"tg" ,"tg-cyrl"  ,"tg-latn"  , "th" ,"ti" , "tk"  ,"tl" ,"tly" ,"tn" , "to" , "tpi" , "tr"  ,"tru"  ,"ts" , "tt" , "tt-cyrl" ,"tt-latn" , "tum" , "tw" , "ty" ,"tyv" , "tzm" ,"udm" ,"ug" , "ug-arab" , "ug-latn" ,"uk" , "ur" , "uz" ,"uz-cyrl" , "uz-latn" , "ve" ,"vec" , "vep" , "vi" ,"vls" ,"vmf" , "vo" ,"vot"  ,"vro" ,"wa" , "war" , "wo" , "wuu" , "xal" , "xh" ,"xmf" ,"yi" , "yo" , "yue" , "za" , "zea" ,"zh" , "zh-classical"  , "zh-cn" , "zh-hans"  , "zh-hant"  , "zh-hk"  , 
             "zh-min-nan"  ,"zh-mo" ,"zh-my"  ,"zh-sg"  ,"zh-tw"  ,"zh-yue"  ,"zu"]

num = 0
PAGES = ['writer','Journalist','architect']
PAGES = ['writer']

for lan in languages:
    try:
        print(lan)
        wikipedia.set_lang(lan)

        for page in PAGES:
            wikipage = wikipedia.page(page, auto_suggest=False,redirect=True )
            
            print ("Page Title: %s" , wikipage.title)
            print ("Page URL: %s" % wikipage.url)

            images = wikipage.images

            for i in images:
                
                if i.endswith('jpg'):
                      load_img = urllib.request.urlretrieve(i,"img/"+page+str(num)+".jpg")
                elif i.endswith('png'):
                      load_img = urllib.request.urlretrieve(i,"img/"+page+str(num)+".png")
                elif i.endswith('svg'):
                      continue                      
                elif i.endswith('gif'):
                      load_img = urllib.request.urlretrieve(i,"img/"+page+str(num)+".gif")
                num +=1
                time.sleep(.5)
    except Exception as e:
        print(e)