| Index: trunk/tools/daily-image-l/dailyimagel.py |
| — | — | @@ -0,0 +1,180 @@ |
| | 2 | +#!/usr/bin/python |
| | 3 | +# -*- coding: utf-8 -*- |
| | 4 | + |
| | 5 | + |
| | 6 | +wget = '''/usr/sfw/bin/wget -S -erobots=off -q -O - ''' |
| | 7 | + |
| | 8 | +todaypotd = r'http://commons.wikimedia.org/w/index.php?title=Commons:Picture_of_the_day/Today&action=purge' |
| | 9 | +urlbase = r'http://commons.wikimedia.org/wiki/' |
| | 10 | +#querycat = 'http://commons.wikimedia.org/w/query.php?what=categories&format=txt&titles=' |
| | 11 | +querycat = 'http://commons.wikimedia.org/w/api.php?action=query&format=txt&prop=categories&titles=' |
| | 12 | +#querylinks = r'http://commons.wikimedia.org/w/query.php?what=imagelinks&ilnamespace=4&format=txt&illimit=300&titles=' |
| | 13 | +querylinks = r'http://commons.wikimedia.org/w/api.php?action=query&format=txt&iunamespace=4&iulimit=500&list=imageusage&iutitle=' |
| | 14 | + |
| | 15 | + |
| | 16 | +import os,sys,re |
| | 17 | +from commands import getoutput |
| | 18 | +from datetime import date |
| | 19 | + |
| | 20 | +repotdcontent = re.compile('<!-- start content -->(.*?)<!-- end content -->', re.DOTALL) |
| | 21 | +reimagename = re.compile('<div class="magnify"><a href="https://www.mediawiki.org/wiki/([^"]*)" class="internal"') |
| | 22 | +recats = re.compile('Category:(.*)') |
| | 23 | +refplinks = re.compile('Commons:Featured pictures/([^c].*)') |
| | 24 | +reqilinks = re.compile('Commons:Quality [Ii]mages/([^c].*)') |
| | 25 | +recaptions = re.compile('<ul>(.*?)</ul>', re.DOTALL) |
| | 26 | +reli = re.compile('</?li[^>]*>') |
| | 27 | +rea = re.compile('</?a[^>]*>') |
| | 28 | +rei = re.compile('</?i>') |
| | 29 | +renocaption = re.compile('\n[^:]*: Template:Potd[^)]*\)') |
| | 30 | + |
| | 31 | +SENDMAIL = "/usr/sbin/sendmail" |
| | 32 | + |
| | 33 | +mailfilename = "/projects/potd/dailyimagel.txt" |
| | 34 | +mailerror = "/projects/potd/mailerror.txt" |
| | 35 | + |
| | 36 | +#mailto = "brianna.laugher@gmail.com" |
| | 37 | +mailto = "daily-image-l@lists.wikimedia.org" |
| | 38 | +#mailto = 'bryan.tongminh@gmail.com' |
| | 39 | + |
| | 40 | +def createmail(): |
| | 41 | + ''' |
| | 42 | + Attempts to create an email at mailfilename. |
| | 43 | + ''' |
| | 44 | + #print "starting" |
| | 45 | + f = getoutput(wget + '--post-data submit "' + todaypotd + '"') |
| | 46 | + #print "got wget output ok" |
| | 47 | + |
| | 48 | + wgetfile = open('/projects/potd/wgetoutput.txt','w') |
| | 49 | + wgetfile.write(f) |
| | 50 | + wgetfile.close() |
| | 51 | + |
| | 52 | + #print "f:",f |
| | 53 | + |
| | 54 | + content = repotdcontent.findall(f) |
| | 55 | + |
| | 56 | + #print "got content ok" |
| | 57 | + |
| | 58 | + # extract image name/url |
| | 59 | + #print len(content) |
| | 60 | + #print "content[0]:",content[0] |
| | 61 | + |
| | 62 | + imagename = reimagename.findall(content[0])[0] |
| | 63 | + imageurl = urlbase + imagename |
| | 64 | + |
| | 65 | + #print "got image name ok" |
| | 66 | + |
| | 67 | + # attempt to determine license status from categories |
| | 68 | + catstext = getoutput(wget + '"' + querycat + imagename + '"') |
| | 69 | + categories = recats.findall(catstext) |
| | 70 | + |
| | 71 | + #print "categories:", categories |
| | 72 | + |
| | 73 | + licenses = {"GFDL":"GNU Free Documentation License", |
| | 74 | + "CC-BY-SA-2.5,2.0,1.0":"Creative Commons Attribution ShareAlike license, all versions", |
| | 75 | + "CC-BY-SA-1.0":"Creative Commons Attribution ShareAlike license, version 1.0", |
| | 76 | + "CC-BY-SA-2.0":"Creative Commons Attribution ShareAlike license, version 2.0", |
| | 77 | + "CC-BY-SA-2.5":"Creative Commons Attribution ShareAlike license, version 2.5", |
| | 78 | + "CC-BY-1.0":"Creative Commons Attribution license, version 1.0", |
| | 79 | + "CC-BY-2.0":"Creative Commons Attribution license, version 2.0", |
| | 80 | + "CC-BY-2.5":"Creative Commons Attribution license, version 2.5" |
| | 81 | + } |
| | 82 | + |
| | 83 | + lic = "" |
| | 84 | + if "Self-published work" in categories: |
| | 85 | + lic = "Created by a Wikimedian (see image page for details); " |
| | 86 | + for l in licenses.keys(): |
| | 87 | + if l in categories: |
| | 88 | + lic += "Licensed under the " + licenses[l] +'. ' |
| | 89 | + |
| | 90 | + if "Public domain" in categories: |
| | 91 | + lic = "Public domain" |
| | 92 | + |
| | 93 | + for cat in categories: |
| | 94 | + if cat.startswith("PD"): |
| | 95 | + if cat=="PD-self": |
| | 96 | + lic = "Created by a Wikimedian (see image page for details); released into the public domain." |
| | 97 | + elif cat=="PD Art": |
| | 98 | + lic = "Reproduction of a two-dimensional work of art whose copyright has expired (public domain)." |
| | 99 | + elif cat=="PD Old": |
| | 100 | + lic = "Public domain (copyright expired due to the age of the work)." |
| | 101 | + else: |
| | 102 | + lic = "Public domain as a work of the " + cat[3:] + " organisation." |
| | 103 | + |
| | 104 | + # determine FP category (or 'topic') |
| | 105 | + linkstext = getoutput(wget + '"' + querylinks + imagename + '"') |
| | 106 | + isFP = True |
| | 107 | + try: |
| | 108 | + topics = refplinks.findall(linkstext)[0] |
| | 109 | + except IndexError: |
| | 110 | + try: |
| | 111 | + isFP = False |
| | 112 | + topics = reqilinks.findall(linkstext)[0] |
| | 113 | + except IndexError: |
| | 114 | + print "Could not find FP or QI backlink, aborting" |
| | 115 | + raise IndexError, 'Could not find FP or QI backlink' |
| | 116 | + |
| | 117 | + if '/' in topics: |
| | 118 | + topic = topics.split('/')[0] + ' (' + topics.split('/')[1] + ')' |
| | 119 | + else: |
| | 120 | + topic = topics |
| | 121 | + |
| | 122 | + # extract multilingual captions |
| | 123 | + try: |
| | 124 | + captions = recaptions.findall(content[0])[0] |
| | 125 | + except IndexError: |
| | 126 | + raise IndexError, 'no captions??' |
| | 127 | + |
| | 128 | + #print captions |
| | 129 | + captions = reli.sub('',captions) |
| | 130 | + captions = rea.sub('',captions) |
| | 131 | + captions = rei.sub('',captions) |
| | 132 | + captions = renocaption.sub('',captions) |
| | 133 | + |
| | 134 | + |
| | 135 | + # write info to file |
| | 136 | + g= open(mailfilename,'w') |
| | 137 | + g.write("To: " + mailto + '\n') |
| | 138 | + g.write('Content-Type: text/plain; charset=utf-8\r\n') |
| | 139 | + #don't need this? |
| | 140 | + #g.write("From: brianna.laugher@gmail.com\n") |
| | 141 | + g.write("Subject: " + str(date.today()) + '\r\n\r\n') |
| | 142 | + g.write("Body of email:\r\n") |
| | 143 | + |
| | 144 | + g.write(imageurl + '\n') |
| | 145 | + g.write('Copyright status: ' + lic + '\n') |
| | 146 | + if isFP: |
| | 147 | + g.write('Featured Picture category: ' + topic + '\n\n') |
| | 148 | + else: |
| | 149 | + if 'Subject' in topic: |
| | 150 | + g.write('Recognised as a Quality Image due to subject matter\n\n') |
| | 151 | + else: |
| | 152 | + g.write('Recognised as a Quality Image due to technical merit\n\n') |
| | 153 | + g.write('Descriptions:\n') |
| | 154 | + g.write(captions) |
| | 155 | + g.close() |
| | 156 | + return |
| | 157 | + |
| | 158 | +############################### |
| | 159 | +error = None |
| | 160 | +try: |
| | 161 | + createmail() |
| | 162 | +except: |
| | 163 | + # some Python error, catch its name and send error mail |
| | 164 | + error = sys.exc_info()[0] |
| | 165 | + mailfilename = mailerror |
| | 166 | + |
| | 167 | +# get the email message from a file |
| | 168 | +f = open(mailfilename, 'r') |
| | 169 | +mail = f.read() |
| | 170 | +f.close() |
| | 171 | + |
| | 172 | +if error: |
| | 173 | + mail += "Error information: " + str(error) |
| | 174 | + |
| | 175 | +# open a pipe to the mail program and |
| | 176 | +# write the data to the pipe |
| | 177 | +p = os.popen("%s -t" % SENDMAIL, 'w') |
| | 178 | +p.write(mail) |
| | 179 | +exitcode = p.close() |
| | 180 | +if exitcode: |
| | 181 | + print "sendmail error: Exit code: %s" % exitcode |
| Property changes on: trunk/tools/daily-image-l/dailyimagel.py |
| ___________________________________________________________________ |
| Name: svn:eol-style |
| 1 | 182 | + native |