This repository has been archived by the owner on Dec 17, 2017. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathcommonsdownloader.py
155 lines (143 loc) · 8.89 KB
/
commonsdownloader.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
#!/usr/bin/env python2
# -*- coding: utf8 -*-
# Copyright (C) 2011-2012 WikiTeam
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
import csv
import datetime
try:
from hashlib import md5
except ImportError: # Python 2.4 compatibility
from md5 import new as md5
import os
import re
import sys
import urllib
def welcome():
""" """
print "#"*73
print """# Welcome to CommonsDownloader 0.1 by WikiTeam (GPL v3) #
# More info at: http://code.google.com/p/wikiteam/ #"""
print "#"*73
print ''
print "#"*73
print """# Copyright (C) 2011-2012 WikiTeam #
# This program is free software: you can redistribute it and/or modify #
# it under the terms of the GNU General Public License as published by #
# the Free Software Foundation, either version 3 of the License, or #
# (at your option) any later version. #
# #
# This program is distributed in the hope that it will be useful, #
# but WITHOUT ANY WARRANTY; without even the implied warranty of #
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the #
# GNU General Public License for more details. #
# #
# You should have received a copy of the GNU General Public License #
# along with this program. If not, see <http://www.gnu.org/licenses/>. #"""
print "#"*73
print ''
def bye():
""" """
print "---> Congratulations! Your dump is complete <---"
print "If you found any bug, report a new issue here (Google account required): http://code.google.com/p/wikiteam/issues/list"
print "If this is a public wiki, please, consider sending us a copy of this dump. Contact us at http://code.google.com/p/wikiteam"
print "Good luck! Bye!"
def main():
welcome()
filenamefeed = 'commonssql.csv' # feed
#filenamefeed = 'a.csv'
startdate = ''
enddate = ''
delta = datetime.timedelta(days=1) #chunks by day
filenamelimit = 100 #do not change!!!
if len(sys.argv) == 1:
print 'Usage example: python script.py 2005-01-01 2005-01-10 [to download the first 10 days of 2005]'
sys.exit()
elif len(sys.argv) == 2: #use sys.argv[1] as start and enddata, just download a day
startdate = datetime.datetime.strptime(sys.argv[1], '%Y-%m-%d')
enddate = datetime.datetime.strptime(sys.argv[1], '%Y-%m-%d')
elif len(sys.argv) == 3:
startdate = datetime.datetime.strptime(sys.argv[1], '%Y-%m-%d')
enddate = datetime.datetime.strptime(sys.argv[2], '%Y-%m-%d')
else:
sys.exit()
print "Downloading Wikimedia Commons files from %s to %s" % (startdate.strftime('%Y-%m-%d'), enddate.strftime('%Y-%m-%d'))
while startdate <= enddate:
print '== %s ==' % (startdate.strftime('%Y-%m-%d'))
savepath = startdate.strftime('%Y/%m/%d')
filenamecsv = startdate.strftime('%Y-%m-%d.csv')
filenamezip = startdate.strftime('%Y-%m-%d.zip')
c = 0
f = csv.reader(open(filenamefeed, 'r'), delimiter='|', quotechar='"', quoting=csv.QUOTE_MINIMAL)
for img_name, img_timestamp, img_user, img_user_text, img_size, img_width, img_height in f:
if img_timestamp.startswith(startdate.strftime('%Y%m%d')):
if not c: #first loop
try: #create savepath if not exists
os.makedirs(savepath)
except:
pass
#csv header
h = open(filenamecsv, 'w')
h.write('img_name|img_saved_as|img_timestamp|img_user|img_user_text|img_size|img_width|img_height\n')
h.close()
img_name = unicode(img_name, 'utf-8')
img_user_text = unicode(img_user_text, 'utf-8')
original_name = img_name
if re.search(ur"(?m)^\d{14}\!", original_name): #removing 20101005024534! (or similar) from name if present
original_name = original_name[15:]
# quote weird chars to avoid errors while wgetting
img_name_quoted = urllib.quote(re.sub(r' ', r'_', img_name.encode('utf-8')))
# _ ending variables contains no spaces, and \" for command line
img_name_ = re.sub(r'"', r'\"', re.sub(r' ', r'_', img_name.encode('utf-8'))) # do not use ur'', it is encoded
original_name_ = re.sub(r'"', r'\"', re.sub(r' ', r'_', original_name.encode('utf-8'))) # do not use ur'', it is encoded
md5hash = md5(re.sub(' ', '_', original_name.encode("utf-8"))).hexdigest() # do not use image_name, md5 needs the original name and without \"
img_saved_as = ''
img_saved_as_ = ''
if len(img_name) > filenamelimit: #truncate filename if it is long
img_saved_as = img_name[:filenamelimit] + md5(re.sub(' ', '_', img_name.encode('utf-8'))).hexdigest() + '.' + img_name.split('.')[-1]
img_saved_as = re.sub(r' ', r'_', img_saved_as) # do not use ur'', it is encoded
img_saved_as_ = re.sub(r'"', r'\"', re.sub(r' ', r'_', img_saved_as.encode('utf-8'))) # do not use ur'', it is encoded
else:
img_saved_as = re.sub(r' ', r'_', img_name) # do not use ur'', it is encoded
img_saved_as_ = re.sub(r'"', r'\"', re.sub(r' ', r'_', img_name.encode('utf-8'))) # do not use ur'', it is encoded
print img_name, img_saved_as, img_timestamp
#wget file
if original_name != img_name: #the image is an old version, download using /archive/ path in server
os.system('wget -c "http://upload.wikimedia.org/wikipedia/commons/archive/%s/%s/%s" -O "%s/%s"' % (md5hash[0], md5hash[0:2], img_name_quoted, savepath, img_saved_as_))
try:
if not os.path.getsize('%s/%s' % (savepath, img_saved_as_)): #empty file?...
#probably false 20101005024534! begining like this http://commons.wikimedia.org/wiki/File:20041028210012!Pilar.jpg
#ok, restore original_name to ! version and recalculate md5 and other variables that use original_name as source
original_name = img_name
original_name_ = re.sub(r'"', r'\"', re.sub(r' ', r'_', original_name.encode('utf-8')))
md5hash = md5(re.sub(' ', '_', original_name.encode("utf-8"))).hexdigest()
#redownload, now without /archive/ subpath
os.system('wget -c "http://upload.wikimedia.org/wikipedia/commons/%s/%s/%s" -O "%s/%s"' % (md5hash[0], md5hash[0:2], img_name_quoted, savepath, img_saved_as_))
except OSError:
pass
else:
# Issue #66 : try your.org first
os.system('wget -c "http://ftpmirror.your.org/pub/wikimedia/images/wikipedia/commons/%s/%s/%s" -O "%s/%s"' % (md5hash[0], md5hash[0:2], img_name_quoted, savepath, img_saved_as_))
os.system('wget -c "http://upload.wikimedia.org/wikipedia/commons/%s/%s/%s" -O "%s/%s"' % (md5hash[0], md5hash[0:2], img_name_quoted, savepath, img_saved_as_))
#curl .xml description page with full history
os.system('curl -d "&pages=File:%s&history=1&action=submit" http://commons.wikimedia.org/w/index.php?title=Special:Export -o "%s/%s.xml"' % (original_name_, savepath, img_saved_as_))
#save csv info
g = csv.writer(open(filenamecsv, 'a'), delimiter='|', quotechar='"', quoting=csv.QUOTE_MINIMAL)
g.writerow([img_name.encode('utf-8'), img_saved_as.encode('utf-8'), img_timestamp, img_user, img_user_text.encode('utf-8'), img_size, img_width, img_height])
c += 1
#zip downloaded files; add mT to the options if you want to save space by removing the downloaded files day by day; commonschecker needs only zip and csv
os.system('zip -9r %s %s/' % (filenamezip, savepath))
startdate += delta
bye()
if __name__ == "__main__":
main()