def read_djvu(book_name, cached_text, datas, opt):
from match_and_split import align
data = align.get_djvu(cached_text, opt.site, book_name, True)
for pos, text in enumerate(data):
text = re.sub(u'(?ms)<noinclude>(.*?)</noinclude>', u'', text)
datas.setdefault(pos + 1, [])
datas[pos + 1].append(text)
def read_djvu(book_name, cached_text, datas, opt):
from match_and_split import align
data = align.get_djvu(cached_text, opt.site, book_name, True)
for pos, text in enumerate(data):
text = re.sub(u'(?ms)<noinclude>(.*?)</noinclude>', u'', text)
datas.setdefault(pos + 1, [])
datas[pos + 1].append(text)
def do_extract(mysite, maintitle, user, codelang, cache):
prefix = unicode(page_prefixes['wikisource'].get(codelang), 'utf-8')
if not prefix:
return ret_val(E_ERROR, "no prefix")
djvuname = maintitle.replace(u' ', u'_')
print djvuname.encode('utf-8')
text_layer = align.get_djvu(cache, mysite, djvuname, True)
if not text_layer:
return ret_val(E_ERROR, "unable to retrieve text layer")
text = u''
for pos, page_text in enumerate(text_layer):
text += u'==[[' + prefix + u':' + maintitle + u'/' + unicode(pos+1) + u']]==\n'
text += page_text + u'\n'
page = pywikibot.Page(mysite, u'User:'******'/Text')
safe_put(page, text, comment = u'extract text')
return ret_val(E_OK, "")
def do_extract(mysite, maintitle, user, codelang, cache):
prefix = unicode(page_prefixes['wikisource'].get(codelang), 'utf-8')
if not prefix:
return ret_val(E_ERROR, "no prefix")
djvuname = maintitle.replace(u' ', u'_')
print djvuname.encode('utf-8')
text_layer = align.get_djvu(cache, mysite, djvuname, True)
if not text_layer:
return ret_val(E_ERROR, "unable to retrieve text layer")
text = u''
for pos, page_text in enumerate(text_layer):
text += u'==[[' + prefix + u':' + maintitle + u'/' + unicode(
pos + 1) + u']]==\n'
text += page_text + u'\n'
page = pywikibot.Page(mysite, u'User:'******'/Text')
safe_put(page, text, comment=u'extract text')
return ret_val(E_OK, "")
