def get_embed_code(url, maxwidth=None, maxheight=None):
embed = {}
header = cache.get_headers(url)
if header.get('content-type', '').startswith('text/html'):
html = cache.read_url(url)
json_oembed = filter(lambda l: 'json+oembed' in l, re.compile('<link.*?>').findall(html))
xml_oembed = filter(lambda l: 'xml+oembed' in l, re.compile('<link.*?>').findall(html))
if json_oembed:
oembed_url = find_re(json_oembed[0], 'href="(.*?)"')
if maxwidth:
oembed_url += '&maxwidth=%d' % maxwidth
if maxheight:
oembed_url += '&maxheight=%d' % maxheight
embed = json.loads(cache.read_url(oembed_url))
elif xml_oembed:
oembed_url = find_re(json_oembed[0], 'href="(.*?)"')
if maxwidth:
oembed_url += '&maxwidth=%d' % maxwidth
if maxheight:
oembed_url += '&maxheight=%d' % maxheight
data = cache.read_url(oembed_url)
for e in ET.fromstring(data):
embed[e.tag] = e.text
return embed
def parse_movie_path(path):
"""
"A/Abrams, J.J.; Lieber, Jeffrey; Lindelof, Damon/Lost (2004)/Lost.Season 3.Episode 21.Greatest Hits.avi"
"B/Balada, Ivan/Metrum (1967)/Metrum.Part 1.en.srt"
"N/Nakata, Hideo/L - Change the World (2008)/L - Change the World.Part 2.srt"
"R/Reitz, Edgar/Heimat (1984-2006)/Heimat.Season 2.Episode 8.The Wedding.Part 2.avi"
"F/Feuillade, Louis/Les vampires (1915)/Les vampires.Episode 10.Part 2.avi"
title: 'Les vampires', year: '1915', episode: 10, part: 2
"G/Godard, Jean-Luc/Histoire(s) du cinema_ Toutes les histoires (1988)/Histoire(s) du cinema_ Toutes les histoires.avi"
"G/Godard, Jean-Luc/Six fois deux (1976)/Six fois deux.Part 1A.Y a personne.avi"
"G/Godard, Jean-Luc; Miéville, Anne-Marie/France_tour_detour_deux_enfants (1977)/France_tour_detour_deux_enfants.Part 5.Impression_Dictée.avi"
"L/Labarthe, André S_/Cinéastes de notre temps (1964-)/Cinéastes de notre temps.Episode.Jean Renoir le patron, première partie_ La Recherche du relatif.avi"
"S/Scott, Ridley/Blade Runner (1982)/Blade Runner.Directors's Cut.avi"
or
T/Title (Year)/Title.avi
"""
episodeTitle = episodeYear = seriesTitle = None
episodeDirector = []
parts = path.split('/')
#title/year
if len(parts) == 4:
title = parts[2]
elif len(parts) > 1:
title = parts[1]
else:
title = parts[0]
title = title.replace('_ ', ': ')
if title.endswith('_'):
title = title[:-1] + '.'
if title.startswith('_'):
title = '.' + title[1:]
year = find_re(title, '(\(\d{4}\))')
if not year:
year = find_re(title, '(\(\d{4}-\d*\))')
if year and title.endswith(year):
title = title[:-len(year)].strip()
year = year[1:-1]
if '-' in year:
year = find_re(year, '\d{4}')
#director
if len(parts) == 4:
director = parts[1]
if director.endswith('_'):
director = "%s." % director[:-1]
director = director.split('; ')
director = [normalize_name(d).strip() for d in director]
director = filter(lambda d: d not in ('Unknown Director', 'Various Directors'), director)
else:
director = []
#extension/language
fileparts = [x.replace('||', '. ') for x in parts[-1].replace('. ', '||').split('.')]
extension = len(fileparts) > 1 and fileparts[-1] or ''
if len(fileparts) > 1 and len(fileparts[-2]) == 2:
language = fileparts[-2]
else:
language = ''
#season/episode/episodeTitle
match = re.compile('(.+?) \((S(\d+))?(E(\d+))?\)( (.+?))?\.').match(parts[-1])
if match:
seriesTitle = match.group(1)
season = match.group(3)
episode = match.group(5)
episodeTitle = (match.group(6) or '').strip()
if episode != None:
episode = int(episode)
if season != None:
season = int(season)
if episode and not season:
season = 1
else:
season = find_re(parts[-1], '\.Season (\d+)\.')
if season:
season = int(season)
else:
season = None
episode = find_re(parts[-1], '\.Episode[s]* ([\d+]+)\.')
if episode:
episode = episode.split('+')[0]
episode = int(episode)
else:
episode = None
if episode and 'Episode %d'%episode in fileparts:
episodeTitle = fileparts.index('Episode %d' % episode) + 1
episodeTitle = fileparts[episodeTitle]
if episodeTitle == extension or episodeTitle.startswith('Part'):
episodeTitle = None
if not season and 'Episode' in fileparts:
episodeTitle = fileparts.index('Episode') + 1
episodeTitle = fileparts[episodeTitle]
if episodeTitle == extension or episodeTitle.startswith('Part'):
episodeTitle = None
else:
season = 1
if season:
seriesTitle = title
title = u'%s (S%02d)' % (seriesTitle, season)
if isinstance(episode, int):
title = u'%s (S%02dE%02d)' % (seriesTitle, season, episode)
if episodeTitle:
title = u'%s %s' % (title, episodeTitle)
#part
part = find_re(parts[-1], '\.Part (\d+)\.')
if part:
part = int(part)
else:
part = 0
return {
'director': director,
'episodeDirector': episodeDirector,
'episode': episode,
'episodeTitle': episodeTitle,
'episodeYear': episodeYear,
'extension': extension,
'language': language,
'part': part,
'season': season,
'seriesTitle': seriesTitle,
'title': title,
'year': year,
}
