def get_movie_urls(self, title, year=None):
try:
title = deogonkify(title)
s = "Fetching: " + title
logger.info(s)
query_url = 'http://fdb.pl/szukaj?query=' + urllib.quote_plus(
title)
contents = urllib.urlopen(query_url).read()
results = []
for line in contents.split('\n'):
line_match = re.match(
'^\s*<a href="http://fdb.pl/film/(\d+-[^"]+)">(.*) \((\d{4}(?:/I+)?)\)</a>\s*$',
line)
if not line_match:
continue
result_url = 'http://fdb.pl/film/' + line_match.group(
1).strip()
result_title = line_match.group(2).strip()
result_year = line_match.group(3).strip()
if (year == None) or (str(year)[0:4] == result_year[0:4]):
results += [{
'url': result_url,
'title': result_title,
'year': result_year
}]
return results
except Exception, e:
logger.exception(e)
def get_movie_urls(self, title, year = None):
try:
title = deogonkify(title)
query_url = 'http://www.filmweb.pl/szukaj?c=film&q=' + urllib.quote_plus(title)
contents = urllib.urlopen(query_url).read()
results = []
continued = False
for line in contents.split('\n'):
if continued:
continued = False
line_match = re.match('^\s*\((\d{4})\).*$', line)
if not line_match:
continue
result_year = line_match.group(1).strip()
if (year == None) or (str(year)[0:4] == result_year[0:4]):
results += [{'url': result_url, 'title': result_title, 'year': result_year}]
line_match = re.match('^\s*<a class="searchResultTitle" href="([^"]+)">(.*)</a>\s*$', line)
if not line_match:
continue
result_url = line_match.group(1).strip()
result_title = line_match.group(2).strip()
continued = True
return results
except Exception, e:
logger.exception(e)
def get_movie_urls(self, title, year=None):
try:
title = deogonkify(title)
query_url = 'http://www.filmweb.pl/szukaj?c=film&q=' + urllib.quote_plus(
title)
contents = urllib.urlopen(query_url).read()
results = []
continued = False
for line in contents.split('\n'):
if continued:
continued = False
line_match = re.match('^\s*\((\d{4})\).*$', line)
if not line_match:
continue
result_year = line_match.group(1).strip()
if (year == None) or (str(year)[0:4] == result_year[0:4]):
results += [{
'url': result_url,
'title': result_title,
'year': result_year
}]
line_match = re.match(
'^\s*<a class="searchResultTitle" href="([^"]+)">(.*)</a>\s*$',
line)
if not line_match:
continue
result_url = line_match.group(1).strip()
result_title = line_match.group(2).strip()
continued = True
return results
except Exception, e:
logger.exception(e)
def __init__(self, *args, **kw):
from film20.utils.texts import deogonkify
initial = kw.get("initial")
if initial and "username" in initial:
initial["username"] = re.sub("[^\w]", "", deogonkify(unicode(initial["username"])))
super(SSORegistrationForm, self).__init__(*args, **kw)
def get_movie_urls(self, title, year=None):
title = deogonkify(title)
s = "Fetching: " + title
logger.info(s)
query_url = "http://uk.rottentomatoes.com/search/full_search.php?search=" + urllib.quote_plus(
title)
try:
# windows-1252
contents = (codecs.getreader("windows-1252")(
urllib.urlopen(query_url))).read()
results = []
continued = False
for line in contents.split('\n'):
if continued:
line_match = re.match(
'^\s*<td class="lastCol date" width="15%"><p><strong>(\d{4})<\/strong><\/p><\/td>.*$',
line)
if not line_match:
continue
result_year = line_match.group(1).strip()
# only record the result if the year matches (or is null)
if (year == None) or (str(year)[0:4] == result_year[0:4]):
results += [{
'url': result_url,
'title': result_title,
'year': result_year
}]
else:
continued = False
else:
line_match = re.match(
'^\s*<a href="/m/([^"]+)">(.+)</a>\s*$', line)
if not line_match:
continue
result_url = "http://rottentomatoes.com/m/" + line_match.group(
1).strip()
# result_title = line_match.group(2).strip()
result_title = title
continued = True
return results
except UnicodeDecodeError, e:
logger.exception(e)
return None
def get_movie_urls(self, title, year = None):
try:
title = deogonkify(title)
s = "Fetching: " + title
logger.info(s)
query_url = 'http://fdb.pl/szukaj?query=' + urllib.quote_plus(title)
contents = urllib.urlopen(query_url).read()
results = []
for line in contents.split('\n'):
line_match = re.match('^\s*<a href="http://fdb.pl/film/(\d+-[^"]+)">(.*) \((\d{4}(?:/I+)?)\)</a>\s*$', line)
if not line_match:
continue
result_url = 'http://fdb.pl/film/' + line_match.group(1).strip()
result_title = line_match.group(2).strip()
result_year = line_match.group(3).strip()
if (year == None) or (str(year)[0:4] == result_year[0:4]):
results += [{'url': result_url, 'title': result_title, 'year': result_year}]
return results
except Exception, e:
logger.exception(e)
def get_movie_urls(self, title, year = None):
title = deogonkify(title)
s = "Fetching: " + title
logger.info(s)
query_url = "http://uk.rottentomatoes.com/search/full_search.php?search=" + urllib.quote_plus(title)
try:
# windows-1252
contents = (codecs.getreader("windows-1252")(urllib.urlopen(query_url))).read()
results = []
continued = False
for line in contents.split('\n'):
if continued:
line_match = re.match('^\s*<td class="lastCol date" width="15%"><p><strong>(\d{4})<\/strong><\/p><\/td>.*$', line)
if not line_match:
continue
result_year = line_match.group(1).strip()
# only record the result if the year matches (or is null)
if (year == None) or (str(year)[0:4] == result_year[0:4]):
results += [{'url': result_url, 'title': result_title, 'year': result_year}]
else:
continued = False
else:
line_match = re.match('^\s*<a href="/m/([^"]+)">(.+)</a>\s*$', line)
if not line_match:
continue
result_url = "http://rottentomatoes.com/m/"+line_match.group(1).strip()
# result_title = line_match.group(2).strip()
result_title = title
continued = True
return results
except UnicodeDecodeError, e:
logger.exception(e)
return None
def format(cls, txt):
from film20.utils.texts import deogonkify
return str(deogonkify(txt)[0:160])
def format(cls, txt):
from film20.utils.texts import deogonkify
return str(deogonkify(txt)[0:160])
def clean_username(username):
from film20.utils.texts import deogonkify
return re.sub("[^\w]", "", deogonkify(unicode(username)))
