[0-9]{4})',
# Original movie title
'otitle' : 'Titre original *: *(?P.+?)',
'plot' : """(?s) *(?P.+?) *""",
'image' : """ (?P.*?)</a>""" % self.__basePath, self.__data)
if not matchList: return None
return matchList
def __fetchMovieInfo(self, url):
"""
Looks for movie information
"""
self.__getHTMLContent(url)
matches = data = {}
for name, regexp in self.__regExps.iteritems():
if name == 'image':
matches[name] = re.findall(self.__regExps[name], self.__data, re.S | re.I)
else:
matches[name] = re.search(regexp, self.__data)
if matches[name]:
if name == 'title':
data[name] = matches[name].group('title').strip()
elif name == 'dirs':
dirsList = re.sub('</?a.*?>', '', matches[name].group('step1')).split(',')
data[name] = []
for d in dirsList:
data[name].append(d.strip())
elif name == 'actors':
actorsList = re.sub('</?a.*?>', '', matches[name].group('step1')).split(',')
data[name] = []
for d in actorsList:
data[name].append(d.strip())
elif name == 'nat':
data[name] = matches[name].group('nat').strip()
elif name == 'genres':
genresList = re.sub('</?a.*?>', '', matches[name].group('step1')).split(',')
data[name] = []
for d in genresList:
data[name].append(d.strip())
elif name == 'time':
h, m = matches[name].group('hours'), matches[name].group('mins')
totmin = int(h)*60+int(m)
data[name] = str(totmin)
elif name == 'year':
data[name] = matches[name].group('year').strip()
elif name == 'otitle':
data[name] = matches[name].group('otitle').strip()
elif name == 'plot':
data[name] = matches[name].group('plot').strip()
# Image path
elif name == 'image':
# Save image to a temporary folder
md5 = genMD5()
imObj = urllib2.urlopen(matches[name][0].strip())
img = imObj.read()
imObj.close()
imgPath = "/tmp/%s.jpeg" % md5
try:
f = open(imgPath, 'w')
f.write(img)
f.close()
except:
# Could be great if we can pass exit code and some message
# to tellico in case of failure...
pass
data[name] = (md5 + '.jpeg', base64.encodestring(img))
# Delete temporary image
try:
os.remove(imgPath)
except:
# Could be great if we can pass exit code and some msg
# to tellico in case of failure...
pass
else:
matches[name] = ''
return data
def __getMovie(self, title):
if not len(title): return
self.__title = title
self.__getHTMLContent(self.__searchURL % urllib.quote(self.__title))
# Get all links
links = self.__fetchMovieLinks()
# Now retrieve infos
if links:
for entry in links:
data = self.__fetchMovieInfo( url = "%s=%s" % (self.__movieURL, entry[0]) )
# Add allocine link (custom field)
data['allocine'] = "%s=%s" % (self.__movieURL, entry[0])
self.__domTree.addEntry(data)
else:
return None
def showUsage():
print "Usage: %s movietitle" % sys.argv[0]
sys.exit(1)
def main():
if len(sys.argv) < 2:
showUsage()
parser = AlloCineParser()
parser.run(sys.argv[1])
if __name__ == '__main__':
main()
| |