2
0
mirror of https://github.com/WikiTeam/wikiteam synced 2024-11-04 12:00:28 +00:00

git-svn-id: https://wikiteam.googlecode.com/svn/trunk@49 31edc4fc-5e31-b4c4-d58b-c8bc928bcb95

This commit is contained in:
emijrp 2011-04-09 12:34:07 +00:00
parent 2285c2e0a9
commit 9e397e0464

View File

@ -227,7 +227,7 @@ def getXMLPage(config={}, title=''):
time.sleep(10) time.sleep(10)
f = urllib2.urlopen(req) f = urllib2.urlopen(req)
except: except:
print 'An error have occurred while retrieving', title print 'An error have occurred while retrieving "%s"' % (title)
print 'Please, resume the dump, --resume' print 'Please, resume the dump, --resume'
sys.exit() sys.exit()
xml = f.read() xml = f.read()
@ -297,7 +297,6 @@ def generateXMLDump(config={}, titles=[], start=''):
xmlfile = open('%s/%s' % (config['path'], xmlfilename), 'a') xmlfile = open('%s/%s' % (config['path'], xmlfilename), 'a')
c = 1 c = 1
total = len(titles)
for title in titles: for title in titles:
if title == start: #start downloading from start, included if title == start: #start downloading from start, included
lock = False lock = False
@ -305,7 +304,7 @@ def generateXMLDump(config={}, titles=[], start=''):
continue continue
delay(config=config) delay(config=config)
if c % 10 == 0: if c % 10 == 0:
print ' Downloaded %d pages of %d (%.1f%%)' % (c, total, c/(total/100)) print ' Downloaded %d pages' % (c)
xml = getXMLPage(config=config, title=title) xml = getXMLPage(config=config, title=title)
xml = cleanXML(xml=xml) xml = cleanXML(xml=xml)
xmlfile.write(xml) xmlfile.write(xml)