[cineoob] filter casting and filmo by role

man/cineoob.1

@@ -37,13 +37,13 @@ Get information about a movie.
 .br
 Get information about a person.
 .TP
-\fBfilmography\fR \fIID\fR
+\fBfilmography\fR \fIID\fR \fI[ROLE]\fR
 .br
-List movies related to a person.
+List movies related to a person. If ROLE is given, filter by ROLE.
 .TP
-\fBcasting\fR \fIID\fR
+\fBcasting\fR \fIID\fR \fI[ROLE]\fR
 .br
-List persons related to a movie.
+List persons related to a movie. if ROLE is given, filter by ROLE.
 .TP
 \fBmovies_in_common\fR \fIID1\fR \fIID2\fR
 .br

modules/imdb/backend.py

@@ -51,11 +51,11 @@ class ImdbBackend(BaseBackend, ICapCinema):
     def iter_persons(self, pattern):
         return self.browser.iter_persons(quote_plus(pattern.encode('utf-8')))
 
-    def iter_movie_persons(self, id):
+    def iter_movie_persons(self, id, role):
-        return self.browser.iter_movie_persons(id)
+        return self.browser.iter_movie_persons(id, role)
 
-    def iter_person_movies(self, id):
+    def iter_person_movies(self, id, role):
-        return self.browser.iter_person_movies(id)
+        return self.browser.iter_person_movies(id, role)
 
     def iter_person_movies_ids(self, id):
         return self.browser.iter_person_movies_ids(id)

modules/imdb/browser.py

@@ -133,15 +133,15 @@ class ImdbBrowser(BaseBrowser):
         assert self.is_on_page(BiographyPage)
         return self.page.get_biography()
 
-    def iter_movie_persons(self, movie_id):
+    def iter_movie_persons(self, movie_id, role):
         self.location('http://www.imdb.com/title/%s' % movie_id)
         assert self.is_on_page(MoviePage)
-        return self.page.iter_persons(movie_id)
+        return self.page.iter_persons(movie_id, role)
 
-    def iter_person_movies(self, person_id):
+    def iter_person_movies(self, person_id, role):
         self.location('http://www.imdb.com/name/%s/filmotype' % person_id)
         assert self.is_on_page(FilmographyPage)
-        return self.page.iter_movies()
+        return self.page.iter_movies(role)
 
     def iter_person_movies_ids(self, person_id):
         self.location('http://www.imdb.com/name/%s' % person_id)

modules/imdb/pages.py

@@ -31,10 +31,10 @@ __all__ = ['MoviePage','PersonPage','MovieCrewPage','BiographyPage','Filmography
 class MoviePage(BasePage):
     ''' Page describing a movie, only used to go on the MovieCrewPage
     '''
-    def iter_persons(self,id):
+    def iter_persons(self, id, role=None):
         self.browser.location('http://www.imdb.com/title/%s/fullcredits'%id)
         assert self.browser.is_on_page(MovieCrewPage)
-        for p in self.browser.page.iter_persons():
+        for p in self.browser.page.iter_persons(role):
             yield p
 
     def iter_persons_ids(self,id):
@@ -62,14 +62,26 @@ class BiographyPage(BasePage):
 class MovieCrewPage(BasePage):
     ''' Page listing all the persons related to a movie
     '''
-    def iter_persons(self):
+    def iter_persons(self, role_filter=None):
-        tables = self.parser.select(self.document.getroot(),'table.cast')
+        if (role_filter == None or (role_filter != None and role_filter == 'actor')):
-        if len(tables) > 0:
+            tables = self.parser.select(self.document.getroot(),'table.cast')
-            table = tables[0]
+            if len(tables) > 0:
-            tds = self.parser.select(table,'td.nm')
+                table = tables[0]
-            for td in tds:
+                tds = self.parser.select(table,'td.nm')
-                id = td.find('a').attrib.get('href','').strip('/').split('/')[-1]
+                for td in tds:
-                yield self.browser.get_person(id)
+                    id = td.find('a').attrib.get('href','').strip('/').split('/')[-1]
+                    yield self.browser.get_person(id)
+
+        for gloss_link in self.parser.select(self.document.getroot(),'table[cellspacing=1] h5 a'):
+            role = gloss_link.attrib.get('name','').rstrip('s')
+            if (role_filter == None or (role_filter != None and role == role_filter)):
+                tbody = gloss_link.getparent().getparent().getparent().getparent()
+                for line in self.parser.select(tbody,'tr')[1:]:
+                    for a in self.parser.select(line,'a'):
+                        href = a.attrib.get('href','')
+                        if '/name/nm' in href:
+                            id = href.strip('/').split('/')[-1]
+                            yield self.browser.get_person(id)
 
     def iter_persons_ids(self):
         tables = self.parser.select(self.document.getroot(),'table.cast')
@@ -170,10 +182,11 @@ class FilmographyPage(BasePage):
                     roles[role].append('(%s) %s'%(between_p,a.text))
         return roles
 
-    def iter_movies(self):
+    def iter_movies(self, role_filter=None):
         for role_div in self.parser.select(self.document.getroot(),'div.filmo'):
             role = self.parser.select(role_div,'h5 a',1).text.replace(':','')
-            if role != 'In Development':
+            if (role_filter == None or (role_filter != None and role.lower().strip() == role_filter))\
+            and role != 'In Development':
                 for a in self.parser.select(role_div,'ol > li > a'):
                     id = a.attrib.get('href','').strip('/').split('/')[-1]
                     if id.startswith('tt'):

weboob/applications/cineoob/cineoob.py

@@ -165,11 +165,15 @@ class Cineoob(ReplApplication):
                            'movies_in_common':'movie_list',
                            'persons_in_common':'person_list'
                           }
+    ROLE_LIST = ['actor','director','writer','composer','producer']
 
-    def complete_info(self, text, line, *ignored):
+    def complete_filmography(self, text, line, *ignored):
         args = line.split(' ')
-        if len(args) == 2:
+        if len(args) == 3:
-            return self._complete_object()
+            return self.ROLE_LIST
+
+    def complete_casting(self, text, line, *ignored):
+        return self.complete_filmography(text,line,ignored)
 
     def do_movies_in_common(self, line):
         """
@@ -304,35 +308,39 @@ class Cineoob(ReplApplication):
             self.cached_format(person)
         self.flush()
 
-    def do_casting(self, movie_id):
+    def do_casting(self, line):
         """
-        casting  movie_ID
+        casting  movie_ID  [ROLE]
 
         List persons related to a movie.
+        If ROLE is given, filter by ROLE
         """
+        movie_id, role = self.parse_command_args(line, 2, 1)
+
         movie = self.get_object(movie_id, 'get_movie')
         if not movie:
             print >>sys.stderr, 'Movie not found: %s' % id
             return 3
 
-        self.change_path([u'casting'])
+        for backend, person in self.do('iter_movie_persons', movie.id, role):
-        for backend, person in self.do('iter_movie_persons', movie.id):
             self.cached_format(person)
         self.flush()
 
-    def do_filmography(self, person_id):
+    def do_filmography(self, line):
         """
-        filmography  person_ID
+        filmography  person_ID  [ROLE]
 
         List movies of a person.
+        If ROLE is given, filter by ROLE
         """
+        person_id, role = self.parse_command_args(line, 2, 1)
+
         person = self.get_object(person_id, 'get_person')
         if not person:
             print >>sys.stderr, 'Person not found: %s' % id
             return 3
 
-        self.change_path([u'filmography'])
+        for backend, movie in self.do('iter_person_movies', person.id, role):
-        for backend, movie in self.do('iter_person_movies', person.id):
             self.cached_format(movie)
         self.flush()