def ocr_image(cache, url, codelang):
# This is checked in bot_listening but must be redone here, so if
# the ocr for the same page is asked multiple time, we will do the ocr
# only once.
text = get_from_cache(cache, url, codelang)
if text:
return ret_val(0, text)
url = url.encode('utf-8')
cache_key = image_key(url)
lang = ocr.tesseract_languages.get(codelang, 'eng')
basename = os.path.expanduser('~/tmp') + '/tesseract/image_%s' % cache_key
image_filename = basename + ".jpg"
utils.copy_file_from_url(url, image_filename)
if not os.path.exists(image_filename):
return ret_val(1, "could not download url: %s" % url)
text = ocr.ocr(image_filename, basename, lang)
if text == None:
return ret_val(2, "ocr failed")
os.remove(image_filename)
if os.path.exists(basename + ".txt"):
os.remove(basename + ".txt")
cache.set(cache_key, text)
return ret_val(0, text)
def ocr_image(cache, url, codelang):
# This is checked in bot_listening but must be redone here, so if
# the ocr for the same page is asked multiple time, we will do the ocr
# only once.
text = get_from_cache(cache, url, codelang)
if text:
return ret_val(0, text)
url = url.encode('utf-8')
cache_key = image_key(url)
lang = ocr.tesseract_languages.get(codelang, 'eng')
basename = os.path.expanduser('~/tmp') + '/tesseract/image_%s' % cache_key
image_filename = basename + ".jpg"
utils.copy_file_from_url(url, image_filename)
if not os.path.exists(image_filename):
return ret_val(1, "could not download url: %s" % url)
text = ocr.ocr(image_filename, basename, lang)
if text == None:
return ret_val(2, "ocr failed")
os.remove(image_filename)
if os.path.exists(basename + ".txt"):
os.remove(basename + ".txt")
cache.set(cache_key, text)
return ret_val(0, text)
def extract_djvu_text(url, filename, sha1):
print "extracting text layer"
if type(filename) == type(u''):
filename = filename.encode('utf-8')
utils.copy_file_from_url(url, filename, sha1)
data = []
# GTK app are very touchy
os.environ['LANG'] = 'en_US.UTF8'
# FIXME: check return code
ls = subprocess.Popen(['djvutxt', filename, '--detail=page'],
stdout=subprocess.PIPE,
close_fds=True)
text = ls.stdout.read()
ls.wait()
for t in re.finditer(
u'\((page -?\d+ -?\d+ -?\d+ -?\d+[ \n]+"(.*)"[ ]*|)\)\n', text):
t = unicode(t.group(1), 'utf-8', 'replace')
t = re.sub(u'^page \d+ \d+ \d+ \d+[ \n]+"', u'', t)
t = re.sub(u'"[ ]*$', u'', t)
t = unquote_text_from_djvu(t)
data.append(t)
os.remove(filename)
return sha1, data
def extract_djvu_text(url, filename, sha1):
print "extracting text layer"
if type(filename) == type(u''):
filename = filename.encode('utf-8')
utils.copy_file_from_url(url, filename, sha1)
data = []
# GTK app are very touchy
os.environ['LANG'] = 'en_US.UTF8'
# FIXME: check return code
ls = subprocess.Popen([ 'djvutxt', filename, '--detail=page'], stdout=subprocess.PIPE, close_fds = True)
text = ls.stdout.read()
ls.wait()
for t in re.finditer(u'\((page -?\d+ -?\d+ -?\d+ -?\d+[ \n]+"(.*)"[ ]*|)\)\n', text):
t = unicode(t.group(1), 'utf-8', 'replace')
t = re.sub(u'^page \d+ \d+ \d+ \d+[ \n]+"', u'', t)
t = re.sub(u'"[ ]*$', u'', t)
t = unquote_text_from_djvu(t)
data.append(t)
os.remove(filename)
return sha1, data
def check_and_upload(url, filename, sha1):
if not os.path.exists(filename) or utils.sha1(filename) != sha1:
if not utils.copy_file_from_url(url, filename, sha1):
return False
return True
if not os.path.exists(out_filename) or ls.returncode:
# in case returncode == 0
print >> sys.stderr, "ocr.ocr() fail to exec tesseract:", ls.returncode, filename
fd = open(out_filename, 'w')
fd.write('An error occurred during ocr processing: ' + filename)
fd.close()
fd = open(out_filename)
txt = fd.read()
fd.close()
if tesseract_data_prefix:
del os.environ['TESSDATA_PREFIX']
if ls.returncode != 0:
print >> sys.stderr, "ocr.ocr() fail to exec tesseract:", ls.returncode, filename
return None
return txt
if __name__ == "__main__":
image_filename = 'temp.jpg'
url= 'https://upload.wikimedia.org/wikipedia/commons/thumb/f/f4/Petitot_-_Collection_compl%C3%A8te_des_m%C3%A9moires_relatifs_%C3%A0_l%E2%80%99histoire_de_France%2C_2e_s%C3%A9rie%2C_tome_45.djvu/page280-1024px-Petitot_-_Collection_compl%C3%A8te_des_m%C3%A9moires_relatifs_%C3%A0_l%E2%80%99histoire_de_France%2C_2e_s%C3%A9rie%2C_tome_45.djvu.jpg'
lang = 'fr'
utils.copy_file_from_url(url, image_filename)
print ocr(image_filename, image_filename, tesseract_languages[lang], config = 'hocr')
os.remove(image_filename)
os.remove(image_filename + ".txt")
def copy_ia_file(ia_id, metadata):
base_url = 'https://archive.org/download/%s/' % ia_id
utils.copy_file_from_url(base_url + metadata['name'], metadata['name'],
expect_sha1 = metadata['sha1'])
def check_and_upload(url, filename, sha1):
if not os.path.exists(filename) or utils.sha1(filename) != sha1:
if not utils.copy_file_from_url(url, filename, sha1):
return False
return True