[cineoob] new command movies_in_common

modules/imdb/backend.py

@@ -56,3 +56,6 @@ class ImdbBackend(BaseBackend, ICapCinema):
 
     def iter_person_movies(self, id):
         return self.browser.iter_person_movies(id)
+
+    def iter_person_movies_ids(self, id):
+        return self.browser.iter_person_movies_ids(id)

modules/imdb/browser.py

@@ -72,7 +72,11 @@ class ImdbBrowser(BaseBrowser):
 
         title = jres['title']
         if jres.has_key('runtime'):
-            duration = int(jres['runtime'][0].split(':')[-1].split()[0])
+            dur_str = jres['runtime'][0].split(':')
+            if len(dur_str) == 1:
+                duration = int(dur_str[0].split()[0])
+            else:
+                duration = int(dur_str[1].split()[0])
         if jres.has_key('also_known_as'):
             for other_t in jres['also_known_as']:
                 if other_t.has_key('country') and other_t.has_key('title'):
@@ -126,3 +130,8 @@ class ImdbBrowser(BaseBrowser):
         self.location('http://www.imdb.com/name/%s' % person_id)
         assert self.is_on_page(PersonPage)
         return self.page.iter_movies(person_id)
+
+    def iter_person_movies_ids(self, person_id):
+        self.location('http://www.imdb.com/name/%s' % person_id)
+        assert self.is_on_page(PersonPage)
+        return self.page.iter_movies_ids(person_id)

modules/imdb/pages.py

@@ -70,7 +70,7 @@ class PersonPage(BasePage):
             biography = descs[0].text
         names = self.parser.select(td_overview,'h1[itemprop=name]')
         if len(names) > 0:
-            name = names[0].text
+            name = names[0].text.strip()
         times = self.parser.select(td_overview,'time[itemprop=birthDate]')
         if len(times) > 0:
             time = times[0].attrib.get('datetime','').split('-')
@@ -96,3 +96,9 @@ class PersonPage(BasePage):
             a = self.parser.select(movie_div,'b a',1)
             id = a.attrib.get('href','').strip('/').split('/')[-1]
             yield self.browser.get_movie(id)
+
+    def iter_movies_ids(self,person_id):
+        for movie_div in self.parser.select(self.document.getroot(),'div[class~=filmo-row]'):
+            a = self.parser.select(movie_div,'b a',1)
+            id = a.attrib.get('href','').strip('/').split('/')[-1]
+            yield id