Archives
/
wikiteam
mirror of https://github.com/WikiTeam/wikiteam
2
0
Fork 0
Code Issues Projects Releases Wiki Activity

wikiadownloader: Autopep8fied

Browse Source 
* Made the source look a bit better, though this script might not be
  used anymore.

Signed-off-by: mr.Shu <mr@shu.io>
pull/197/head
mr.Shu 10 years ago
parent b3ef165529
commit f022b02e47
1 changed files with 44 additions and 30 deletions
Show Stats Download Patch File Download Diff File

74
wikipediadownloader.py
Unescape Escape View File

@ -6,12 +6,12 @@
# it under the terms of the GNU General Public License as published by # it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or # the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version. # (at your option) any later version.
# #
# This program is distributed in the hope that it will be useful, # This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of # but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details. # GNU General Public License for more details.
# #
# You should have received a copy of the GNU General Public License # You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>. # along with this program. If not, see <http://www.gnu.org/licenses/>.
@ -22,27 +22,32 @@ import sys
import time import time
import urllib import urllib
def main(): def main():
parser = argparse.ArgumentParser(description='Downloader of Wikimedia dumps') parser = argparse.ArgumentParser(
description='Downloader of Wikimedia dumps')
#parser.add_argument('-f', '--families', help='Choose which family projects to download (e.g. all, wikipedia, wikibooks, wikinews, wikiquote, wikisource, wikivoyage, wiktionary)', required=False) #parser.add_argument('-f', '--families', help='Choose which family projects to download (e.g. all, wikipedia, wikibooks, wikinews, wikiquote, wikisource, wikivoyage, wiktionary)', required=False)
parser.add_argument('-r','--maxretries', help='Max retries to download a dump when md5sum doesn\'t fit. Default: 3', required=False) parser.add_argument(
parser.add_argument('-s','--start', help='Start to download from this project (e.g.: eswiki, itwikisource, etc)', required=False) '-r', '--maxretries', help='Max retries to download a dump when md5sum doesn\'t fit. Default: 3', required=False)
parser.add_argument(
'-s', '--start', help='Start to download from this project (e.g.: eswiki, itwikisource, etc)', required=False)
args = parser.parse_args() args = parser.parse_args()
maxretries = 3 maxretries = 3
if args.maxretries and int(args.maxretries) >= 0: if args.maxretries and int(args.maxretries) >= 0:
maxretries = int(args.maxretries) maxretries = int(args.maxretries)
dumpsdomain = 'http://dumps.wikimedia.org' dumpsdomain = 'http://dumps.wikimedia.org'
f = urllib.urlopen('%s/backup-index.html' % (dumpsdomain)) f = urllib.urlopen('%s/backup-index.html' % (dumpsdomain))
raw = f.read() raw = f.read()
f.close() f.close()
m = re.compile(r'<a href="(?P<project>[^>]+)/(?P<date>\d+)">[^<]+</a>: <span class=\'done\'>Dump complete</span>').finditer(raw) m = re.compile(
r'<a href="(?P<project>[^>]+)/(?P<date>\d+)">[^<]+</a>: <span class=\'done\'>Dump complete</span>').finditer(raw)
projects = [] projects = []
for i in m: for i in m:
projects.append([i.group('project'), i.group('date')]) projects.append([i.group('project'), i.group('date')])
projects.reverse() #download oldest dumps first projects.reverse() # download oldest dumps first
#projects = [['enwiki', '20130805']] #projects = [['enwiki', '20130805']]
start = args.start start = args.start
@ -52,53 +57,62 @@ def main():
print 'Skipping %s, %s' % (project, date) print 'Skipping %s, %s' % (project, date)
continue continue
else: else:
start = '' #reset start = '' # reset
print '-'*50, '\n', 'Checking', project, date, '\n', '-'*50 print '-' * 50, '\n', 'Checking', project, date, '\n', '-' * 50
time.sleep(1) #ctrl-c time.sleep(1) # ctrl-c
f = urllib.urlopen('%s/%s/%s/' % (dumpsdomain, project, date)) f = urllib.urlopen('%s/%s/%s/' % (dumpsdomain, project, date))
htmlproj = f.read() htmlproj = f.read()
#print htmlproj # print htmlproj
f.close() f.close()
for dumpclass in ['pages-meta-history\d*\.xml[^\.]*\.7z']: for dumpclass in ['pages-meta-history\d*\.xml[^\.]*\.7z']:
corrupted = True corrupted = True
maxretries2 = maxretries maxretries2 = maxretries
while corrupted and maxretries2 > 0: while corrupted and maxretries2 > 0:
maxretries2 -= 1 maxretries2 -= 1
m = re.compile(r'<a href="(?P<urldump>/%s/%s/%s-%s-%s)">' % (project, date, project, date, dumpclass)).finditer(htmlproj) m = re.compile(r'<a href="(?P<urldump>/%s/%s/%s-%s-%s)">' %
(project, date, project, date, dumpclass)).finditer(htmlproj)
urldumps = [] urldumps = []
for i in m: #enwiki is splitted in several files, thats why we need a loop here # enwiki is splitted in several files, thats why we need a loop
urldumps.append('%s/%s' % (dumpsdomain, i.group('urldump'))) # here
for i in m:
#print urldumps urldumps.append(
'%s/%s' % (dumpsdomain, i.group('urldump')))
# print urldumps
for urldump in urldumps: for urldump in urldumps:
dumpfilename = urldump.split('/')[-1] dumpfilename = urldump.split('/')[-1]
path = '%s/%s' % (dumpfilename[0], project) path = '%s/%s' % (dumpfilename[0], project)
if not os.path.exists(path): if not os.path.exists(path):
os.makedirs(path) os.makedirs(path)
os.system('wget -c %s -O %s/%s' % (urldump, path, dumpfilename)) os.system('wget -c %s -O %s/%s' %
(urldump, path, dumpfilename))
#md5check
# md5check
os.system('md5sum %s/%s > md5' % (path, dumpfilename)) os.system('md5sum %s/%s > md5' % (path, dumpfilename))
f = open('md5', 'r') f = open('md5', 'r')
raw = f.read() raw = f.read()
f.close() f.close()
md51 = re.findall(r'(?P<md5>[a-f0-9]{32})\s+%s/%s' % (path, dumpfilename), raw)[0] md51 = re.findall(
r'(?P<md5>[a-f0-9]{32})\s+%s/%s' % (path, dumpfilename), raw)[0]
print md51 print md51
f = urllib.urlopen('%s/%s/%s/%s-%s-md5sums.txt' % (dumpsdomain, project, date, project, date)) f = urllib.urlopen(
'%s/%s/%s/%s-%s-md5sums.txt' % (dumpsdomain, project, date, project, date))
raw = f.read() raw = f.read()
f.close() f.close()
f = open('%s/%s-%s-md5sums.txt' % (path, project, date), 'w') f = open('%s/%s-%s-md5sums.txt' %
(path, project, date), 'w')
f.write(raw) f.write(raw)
f.close() f.close()
md52 = re.findall(r'(?P<md5>[a-f0-9]{32})\s+%s' % (dumpfilename), raw)[0] md52 = re.findall(
r'(?P<md5>[a-f0-9]{32})\s+%s' % (dumpfilename), raw)[0]
print md52 print md52
if md51 == md52: if md51 == md52:
print 'md5sum is correct for this file, horay! \o/' print 'md5sum is correct for this file, horay! \o/'
print '\n'*3 print '\n' * 3
corrupted = False corrupted = False
else: else:
os.remove('%s/%s' % (path, dumpfilename)) os.remove('%s/%s' % (path, dumpfilename))

Write Preview
Loading…
Cancel
Save