imdb in progress...

modules/imdb/browser.py

@@ -42,7 +42,8 @@ class ImdbBrowser(BaseBrowser):
         # the api leads to a json result or the html movie page if there is only one result
         self.location('http://www.imdb.com/xml/find?json=1&tt=on&q=%s' % pattern.encode('utf-8'))
         if self.is_on_page(MoviePage):
-            yield self.page.get_movie()
+            id = 'tt'+self.geturl().split('/tt')[1].split('/')[0]
+            yield self.page.get_movie(id)
         else:
             res = self.readurl('http://www.imdb.com/xml/find?json=1&tt=on&q=%s' % pattern.encode('utf-8'))
             jres = json.loads(res)
@@ -51,10 +52,11 @@ class ImdbBrowser(BaseBrowser):
                     yield self.get_movie(m['id'])
 
     def iter_persons(self, pattern):
-        # the api leads to a json result or the html movie page if there is only one result
+        # the api leads to a json result or the html person page if there is only one result
         self.location('http://www.imdb.com/xml/find?json=1&nm=on&q=%s' % pattern.encode('utf-8'))
         if self.is_on_page(PersonPage):
-            yield self.page.get_person()
+            id = 'nm'+self.geturl().split('/nm')[1].split('/')[0]
+            yield self.page.get_person(id)
         else:
             res = self.readurl('http://www.imdb.com/xml/find?json=1&nm=on&q=%s' % pattern.encode('utf-8'))
             jres = json.loads(res)

modules/imdb/pages.py

@@ -33,7 +33,8 @@ class MoviePage(BasePage):
     def get_movie(self,id):
         title = NotAvailable
         duration = NotAvailable
-        description = NotAvailable.__unicode__()
+        release_date = NotAvailable
+        description = NotAvailable
         td_overview = self.parser.select(self.document.getroot(),'td#overview-top',1)
         for span in self.parser.select(td_overview,'h1.header span[itemprop=name]'):
             if span.attrib.get('class','') == 'itemprop':
@@ -42,10 +43,12 @@ class MoviePage(BasePage):
                     title = other_titles
             elif span.attrib.get('class','') == 'title-extra':
                 title = span.text
-        meta = self.parser.select(td_overview,'meta[itemprop=datePublished]',1)
+        metas = self.parser.select(td_overview,'meta[itemprop=datePublished]')
-        datestrings = meta.attrib.get('content','').split('-')
+        if len(metas) > 0:
-        if len(datestrings) == 2:
+            datestrings = metas[0].attrib.get('content','').split('-')
-            datestrings.append('1')
+            if len(datestrings) == 2:
+                datestrings.append('1')
+            release_date = datetime(int(datestrings[0]),int(datestrings[1]),int(datestrings[2]))
         time = self.parser.select(td_overview,'time[itemprop=duration]')
         if len(time) > 0:
             duration = int(time[0].attrib.get('datetime','').strip(string.letters))
@@ -54,7 +57,7 @@ class MoviePage(BasePage):
             description = desc[0].text
         movie = Movie(id,title.strip())
         movie.other_titles    = other_titles.strip()
-        movie.release_date    = datetime(int(datestrings[0]),int(datestrings[1]),int(datestrings[2]))
+        movie.release_date    = release_date
         movie.duration        = duration
         movie.description     = description
         movie.note            = "10/10"
@@ -81,22 +84,55 @@ class MovieCrewPage(BasePage):
                 person.real_name = NotAvailable
                 person.birth_date = NotAvailable
                 person.nationality = NotAvailable
+                person.biography = NotAvailable
                 person.gender = NotAvailable
                 yield person
 
 
 class PersonPage(BasePage):
     def get_person(self,id):
-        person = Person(id,'nameplop')
+        name = NotAvailable
-        person.real_name       = 'rn'
+        biography = NotAvailable
-        person.birth_date      = datetime.now()
+        birth_place = NotAvailable
-        person.birth_place     = "place"
+        birth_date = NotAvailable
-        person.gender          = "M"
+        real_name = NotAvailable
-        person.nationality     = "nn"
+        gender = NotAvailable
-        person.biography       = 'bio'
+        nationality = NotAvailable
+        td_overview = self.parser.select(self.document.getroot(),'td#overview-top',1)
+        descs = self.parser.select(td_overview,'span[itemprop=description]')
+        if len(descs) > 0:
+            biography = descs[0].text
+        names = self.parser.select(td_overview,'h1[itemprop=name]')
+        if len(names) > 0:
+            name = names[0].text
+        times = self.parser.select(td_overview,'time[itemprop=birthDate]')
+        if len(times) > 0:
+            time = times[0].attrib.get('datetime','').split('-')
+            birth_date = datetime(int(time[0]),int(time[1]),int(time[2]))
+
+        person = Person(id,name)
+        person.real_name       = real_name
+        person.birth_date      = birth_date
+        person.birth_place     = birth_place
+        person.gender          = gender
+        person.nationality     = nationality
+        person.biography       = biography
         person.awards          = ["aw1","aw2"]
         person.roles           = {}
         return person
 
     def iter_movies(self,person_id):
-        pass
+        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 self.browser.get_movie(id)
+            #title = a.text
+            #movie = Movie(id,title)
+            #movie.other_titles    = NotAvailable 
+            #movie.release_date    = NotAvailable 
+            #movie.duration        = NotAvailable 
+            #movie.description     = NotAvailable 
+            #movie.note            = NotAvailable 
+            #movie.awards          = NotAvailable 
+            #movie.roles           = NotAvailable
+            #yield movie

weboob/applications/cineoob/cineoob.py

@@ -52,7 +52,7 @@ class MovieInfoFormatter(IFormatter):
             for a in obj.awards:
                 result += ' * %s\n' % a
         result += '\n%sDescription%s\n' % (self.BOLD, self.NC)
-        result += obj.description
+        result += '%s'%obj.description
         return result
 
 
@@ -93,7 +93,10 @@ class PersonInfoFormatter(IFormatter):
         result += 'ID: %s\n' % obj.fullid
         result += 'Real name: %s\n' % obj.real_name
         result += 'Birth date: %s\n' % obj.birth_date
-        age = num_years(obj.birth_date)
+        if obj.birth_date != NotAvailable:
+            age = num_years(obj.birth_date)
+        else:
+            age = NotAvailable
         result += 'Age: %s\n' % age
         result += 'Birth place: %s\n' % obj.birth_place
         result += 'Gender: %s\n' % obj.gender
@@ -109,7 +112,7 @@ class PersonInfoFormatter(IFormatter):
             for a in obj.awards:
                 result += ' * %s\n' % a
         result += '\n%sBiography%s\n' % (self.BOLD, self.NC)
-        result += obj.biography
+        result += '%s'%obj.biography
         return result
 
 

weboob/applications/suboob/suboob.py

@@ -47,7 +47,7 @@ class SubtitleInfoFormatter(IFormatter):
         result += 'LANG: %s\n' % obj.language
         result += 'NB CD: %s\n' % obj.nb_cd
         result += '\n%sDescription%s\n' % (self.BOLD, self.NC)
-        result += obj.description
+        result += '%s'%obj.description
         return result