[radiofrance] handle podcasts

modules/radiofrance/browser.py

@@ -18,7 +18,7 @@
 # along with weboob. If not, see <http://www.gnu.org/licenses/>.
 
 from weboob.browser import PagesBrowser, URL
-from .pages import PlayerPage, JsonPage
+from .pages import RadioPage, JsonPage, PodcastPage
 
 __all__ = ['RadioFranceBrowser']
 
@@ -26,11 +26,12 @@ __all__ = ['RadioFranceBrowser']
 class RadioFranceBrowser(PagesBrowser):
     json_page = URL('sites/default/files/(?P<json_url>.*).json',
                     'player-json/reecoute/(?P<json_url_fip>.*)', JsonPage)
-    player_page = URL('(?P<player>.*)', PlayerPage)
+    podcast_page = URL('podcast09/rss_(?P<podcast_id>.*)\.xml', PodcastPage)
+    radio_page = URL('(?P<page>.*)', RadioPage)
 
     def get_radio_url(self, radio, player):
         self.BASEURL = 'http://www.%s.fr/' % radio
-        return self.player_page.go(player=player).get_url()
+        return self.radio_page.go(page=player).get_url()
 
     def get_current(self, radio, json_url):
         self.BASEURL = 'http://www.%s.fr/' % radio
@@ -53,3 +54,24 @@ class RadioFranceBrowser(PagesBrowser):
         for item in self.get_selection(radio_url, json_url, radio_id):
             if pattern.upper() in item.title.upper():
                 yield item
+
+    def get_podcast_emissions(self, radio_url, podcast_url, split_path):
+        self.BASEURL = 'http://www.%s.fr/' % radio_url
+        if split_path[0] == 'franceinter':
+            return self.radio_page.go(page=podcast_url).get_france_inter_podcast_emissions(split_path=split_path)
+        elif split_path[0] == 'franceculture':
+            return self.radio_page.go(page=podcast_url).get_france_culture_podcast_emissions(split_path=split_path)
+        elif split_path[0] == 'franceinfo':
+            return self.radio_page.go(page=podcast_url).get_france_info_podcast_emissions(split_path=split_path)
+        elif split_path[0] == 'francemusique':
+            return self.radio_page.go(page=podcast_url).get_france_musique_podcast_emissions(split_path=split_path)
+        elif split_path[0] == 'mouv':
+            return self.radio_page.go(page=podcast_url).get_mouv_podcast_emissions(split_path=split_path)
+
+    def get_podcasts(self, podcast_id):
+        self.BASEURL = 'http://radiofrance-podcast.net/'
+        return self.podcast_page.go(podcast_id=podcast_id).iter_podcasts()
+
+    def get_france_culture_podcasts_url(self, url):
+        self.BASEURL = 'http://www.franceculture.fr/podcast/'
+        return self.radio_page.go(page=url).get_france_culture_podcasts_url()

modules/radiofrance/module.py

@@ -48,14 +48,17 @@ class RadioFranceModule(Module, CapRadio, CapCollection, CapAudio):
         'franceinter': {u'title': u'France Inter',
                         u'player': u'player',
                         u'live': u'lecteur_commun_json/timeline',
+                        u'podcast': u'podcasts',
                         u'selection': u'lecteur_commun_json/reecoute-%s' % int(time.mktime(datetime.now().replace(hour=14, minute=0, second=0).timetuple()))},
         'franceculture': {u'title': u'France Culture',
                           u'player': u'player',
                           u'live': u'lecteur_commun_json/timeline',
+                          u'podcast': u'podcasts',
                           u'selection': u'lecteur_commun_json/reecoute-%s' % int(time.mktime(datetime.now().replace(hour=14, minute=0, second=0).timetuple()))},
         'franceinfo': {u'title': u'France Info',
                        u'player': u'player',
                        u'live': u'lecteur_commun_json/timeline',
+                       u'podcast': u'programmes-chroniques/podcasts',
                        u'selection': u'lecteur_commun_json/reecoute-%s' % int(time.mktime(datetime.now().replace(hour=14, minute=0, second=0).timetuple()))},
         'fbidf': {u'title': u'France Bleu Île-de-France (Paris)',
                   u'player': u'player/france-bleu-107-1',
@@ -68,10 +71,12 @@ class RadioFranceModule(Module, CapRadio, CapCollection, CapAudio):
         'francemusique': {u'title': u'France Musique',
                           u'player': u'player',
                           u'live': u'lecteur_commun_json/reecoute-%s' % int(time.mktime(datetime.now().replace(hour=14, minute=0, second=0).timetuple())),
+                          u'podcast': u'emissions',
                           u'selection': u'lecteur_commun_json/reecoute-%s' % int(time.mktime(datetime.now().replace(hour=14, minute=0, second=0).timetuple()))},
         'mouv': {u'title': u'Le Mouv\'',
                  u'player': u'player',
                  u'live': u'lecteur_commun_json/timeline',
+                 u'podcast': u'podcasts',
                  u'selection': u'lecteur_commun_json/reecoute-%s' % int(time.mktime(datetime.now().replace(hour=14, minute=0, second=0).timetuple()))},
         'fbalsace': {u'title': u'France Bleu Alsace (Strasbourg)',
                      u'player': u'player/station/france-bleu-alsace',
@@ -252,7 +257,13 @@ class RadioFranceModule(Module, CapRadio, CapCollection, CapAudio):
     }
 
     def iter_resources(self, objs, split_path):
-        if split_path and split_path[0] == u'francebleu':
+        if len(split_path) == 0:
+            for _id, item in sorted(self._RADIOS.iteritems()):
+                if not _id.startswith('fb'):
+                    yield Collection([_id], item['title'])
+            yield Collection([u'francebleu'], u'France Bleu')
+
+        elif split_path[0] == u'francebleu':
             if len(split_path) == 1:
                 for _id, item in sorted(self._RADIOS.iteritems()):
                     if _id.startswith('fb'):
@@ -264,18 +275,33 @@ class RadioFranceModule(Module, CapRadio, CapCollection, CapAudio):
                         for item in self.browser.get_selection('francebleu', selection_url, _id):
                             yield item
                         break
-        elif len(split_path) == 0:
+
-            for _id, item in sorted(self._RADIOS.iteritems()):
-                if not _id.startswith('fb'):
-                    yield Collection([_id], item['title'])
-            yield Collection([u'francebleu'], u'France Bleu')
         elif len(split_path) == 1:
+            yield Collection([split_path[0], u'selection'], u'Selection')
+            if 'podcast' in self._RADIOS[split_path[0]]:
+                yield Collection([split_path[0], u'podcasts'], u'Podcast')
+
+        elif len(split_path) == 2 and split_path[1] == 'selection':
             for _id, item in sorted(self._RADIOS.iteritems()):
                 if _id == split_path[0]:
                     selection_url = self._RADIOS[_id]['selection']
                     for item in self.browser.get_selection(_id, selection_url, _id):
                         yield item
                     break
+
+        elif len(split_path) == 2 and split_path[1] == 'podcasts':
+            for item in self.browser.get_podcast_emissions(split_path[0],
+                                                           self._RADIOS[split_path[0]]['podcast'],
+                                                           split_path):
+                yield item
+
+        elif len(split_path) == 3:
+            podcasts_url = split_path[-1]
+            if split_path[0] == 'franceculture':
+                podcasts_url = self.browser.get_france_culture_podcasts_url(split_path[-1])
+            for item in self.browser.get_podcasts(podcasts_url):
+                yield item
+
         else:
             raise CollectionNotFound(split_path)
 
@@ -347,6 +373,12 @@ class RadioFranceModule(Module, CapRadio, CapCollection, CapAudio):
             selection_url = self._RADIOS[radio]['selection']
             radio_url = radio if not radio.startswith('fb') else 'francebleu'
             return self.browser.get_audio(_id, radio_url, selection_url, radio)
+        elif radio == 'podcast':
+            m = re.match('audio\.podcast\.(\d*)-.*', _id)
+            if m:
+                for item in self.browser.get_podcasts(m.group(1)):
+                    if _id == item.id:
+                        return item
 
     def iter_radios_search(self, pattern):
         for key, radio in self._RADIOS.iteritems():

modules/radiofrance/pages.py

@@ -17,21 +17,161 @@
 # You should have received a copy of the GNU Affero General Public License
 # along with weboob. If not, see <http://www.gnu.org/licenses/>.
 
-from weboob.browser.elements import ItemElement, DictElement, method
+from weboob.browser.elements import ItemElement, DictElement, ListElement, method
-from weboob.browser.pages import HTMLPage, JsonPage
+from weboob.browser.pages import HTMLPage, JsonPage, XMLPage
 from weboob.browser.filters.json import Dict
-from weboob.browser.filters.standard import Format, CleanText, Join, Env
+from weboob.browser.filters.standard import Format, CleanText, Join, Env, Regexp, Duration
 from weboob.capabilities.audio import BaseAudio, BaseAudioIdFilter
 from weboob.capabilities.image import BaseImage
+from weboob.capabilities.collection import Collection
 
 import time
 from datetime import timedelta
 
 
-class PlayerPage(HTMLPage):
+class PodcastPage(XMLPage):
+    @method
+    class iter_podcasts(ListElement):
+        item_xpath = '//item'
+
+        class item(ItemElement):
+            klass = BaseAudio
+
+            obj_id = BaseAudioIdFilter(Format('podcast.%s',
+                                              Regexp(CleanText('./guid'),
+                                                     'http://media.radiofrance-podcast.net/podcast09/(.*).mp3')))
+            obj_title = CleanText('title')
+            obj_format = u'mp3'
+            obj_url = CleanText('enclosure/@url')
+            obj_description = CleanText('description')
+
+            def obj_author(self):
+                author = self.el.xpath('itunes:author',
+                                       namespaces={'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd'})
+                return CleanText('.')(author[0])
+
+            def obj_duration(self):
+                duration = self.el.xpath('itunes:duration',
+                                         namespaces={'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd'})
+                return Duration(CleanText('.'))(duration[0])
+
+            def obj_thumbnail(self):
+                thumbnail = BaseImage(CleanText('//image[1]/url')(self))
+                thumbnail.url = thumbnail.id
+                return thumbnail
+
+
+class RadioPage(HTMLPage):
     def get_url(self):
         return CleanText('//a[@id="player"][1]/@href')(self.doc)
 
+    def get_france_culture_podcasts_url(self):
+        return Regexp(CleanText('//a[@class="lien-rss"][1]/@href'),
+                      'http://radiofrance-podcast.net/podcast09/rss_(.*).xml')(self.doc)
+
+    @method
+    class get_france_culture_podcast_emissions(ListElement):
+        item_xpath = '//li/h3/a'
+
+        class item(ItemElement):
+            klass = Collection
+
+            def condition(self):
+                return u'/podcast/' in CleanText('./@href')(self)
+
+            def obj_split_path(self):
+                _id = Regexp(CleanText('./@href'), '/podcast/(.*)')(self)
+                self.env['split_path'].append(_id)
+                return self.env['split_path']
+
+            obj_id = Regexp(CleanText('./@href'), '/podcast/(.*)')
+            obj_title = CleanText('.')
+
+    @method
+    class get_france_info_podcast_emissions(ListElement):
+        item_xpath = '//div[@class="emission-gdp"]'
+        ignore_duplicate = True
+
+        class item(ItemElement):
+            klass = Collection
+
+            def obj_split_path(self):
+                _id = Regexp(CleanText('./div/div/div/div/ul/li/a[@class="ico-rss"]/@href'),
+                             'http://radiofrance-podcast.net/podcast09/rss_(.*).xml')(self)
+                self.env['split_path'].append(_id)
+                return self.env['split_path']
+
+            obj_id = Regexp(CleanText('./div/div/div/div/ul/li/a[@class="ico-rss"]/@href'),
+                            'http://radiofrance-podcast.net/podcast09/rss_(.*).xml')
+            obj_title = CleanText('./h2/a')
+
+    @method
+    class get_mouv_podcast_emissions(ListElement):
+        item_xpath = '//div[@class="view-content"]/div'
+
+        class item(ItemElement):
+            klass = Collection
+
+            def condition(self):
+                return CleanText('./div/a[@class="podcast-rss"]/@href')(self) and \
+                    Regexp(CleanText('./div/a[@class="podcast-rss"]/@href'),
+                           'http://radiofrance-podcast.net/podcast09/rss_(.*).xml')(self)
+
+            def obj_split_path(self):
+                _id = Regexp(CleanText('./div/a[@class="podcast-rss"]/@href'),
+                             'http://radiofrance-podcast.net/podcast09/rss_(.*).xml')(self)
+                self.env['split_path'].append(_id)
+                return self.env['split_path']
+
+            obj_id = Regexp(CleanText('./div/a[@class="podcast-rss"]/@href'),
+                            'http://radiofrance-podcast.net/podcast09/rss_(.*).xml')
+            obj_title = CleanText('./h2')
+
+    @method
+    class get_france_musique_podcast_emissions(ListElement):
+        item_xpath = '//div[@class="liste-emissions"]/ul/li'
+
+        class item(ItemElement):
+            klass = Collection
+
+            def condition(self):
+                return CleanText('./div/ul/li/a[@class="ico-rss"]/@href')(self) and\
+                    Regexp(CleanText('./div/ul/li/a[@class="ico-rss"]/@href'),
+                           'http://radiofrance-podcast.net/podcast09/rss_(.*).xml')(self)
+
+            def obj_split_path(self):
+                _id = Regexp(CleanText('./div/ul/li/a[@class="ico-rss"]/@href'),
+                             'http://radiofrance-podcast.net/podcast09/rss_(.*).xml')(self)
+                self.env['split_path'].append(_id)
+                return self.env['split_path']
+
+            obj_id = Regexp(CleanText('./div/ul/li/a[@class="ico-rss"]/@href'),
+                            'http://radiofrance-podcast.net/podcast09/rss_(.*).xml')
+            obj_title = CleanText('./div/h3')
+
+    @method
+    class get_france_inter_podcast_emissions(ListElement):
+        item_xpath = '//div[has-class("item-list")]/ul/li/div/div'
+        ignore_duplicate = True
+
+        class item(ItemElement):
+            klass = Collection
+
+            def condition(self):
+                return CleanText('./div/a[@class="podrss"]/@href')(self) and\
+                    Regexp(CleanText('./div/a[@class="podrss"]/@href'),
+                           'http://radiofrance-podcast.net/podcast09/rss_(.*).xml')(self)
+
+            def obj_split_path(self):
+                _id = Regexp(CleanText('./div/a[@class="podrss"]/@href'),
+                             'http://radiofrance-podcast.net/podcast09/rss_(.*).xml')(self)
+                self.env['split_path'].append(_id)
+                return self.env['split_path']
+
+            obj_id = Regexp(CleanText('./div/a[@class="podrss"]/@href'),
+                            'http://radiofrance-podcast.net/podcast09/rss_(.*).xml')
+            obj_title = CleanText('./h2/a')
+
 
 class JsonPage(JsonPage):
     @method

modules/radiofrance/test.py

@@ -26,7 +26,7 @@ from weboob.capabilities.radio import Radio
 class RadioFranceTest(BackendTest):
     MODULE = 'radiofrance'
 
-    def test_get_radios_and_selections(self):
+    def test_ls_radios_and_selections(self):
         l = list(self.backend.iter_resources(objs=[Radio], split_path=[]))
 
         self.assertTrue(0 < len(l) < 30)
@@ -36,7 +36,7 @@ class RadioFranceTest(BackendTest):
                 streams = self.backend.get_radio(name).streams
                 self.assertTrue(len(streams) > 0)
 
-                l_sel = list(self.backend.iter_resources(objs=[BaseAudio], split_path=[name]))
+                l_sel = list(self.backend.iter_resources(objs=[BaseAudio], split_path=[name, 'selection']))
                 self.assertTrue(len(l_sel) > 0)
                 self.assertTrue(len(l_sel[0].url) > 0)
 
@@ -47,10 +47,23 @@ class RadioFranceTest(BackendTest):
             streams = self.backend.get_radio(radio.split_path[-1]).streams
             self.assertTrue(len(streams) > 0)
 
-            l_sel = list(self.backend.iter_resources(objs=[BaseAudio], split_path=['francebleu', radio.split_path[-1]]))
+            l_sel = list(self.backend.iter_resources(objs=[BaseAudio],
+                                                     split_path=['francebleu',
+                                                                 radio.split_path[-1],
+                                                                 'selection']))
             if len(l_sel) > 0:
                 self.assertTrue(len(l_sel[0].url) > 0)
 
+    def test_podcasts(self):
+        for key, item in self.backend._RADIOS.iteritems():
+            if 'podcast' in item:
+                emissions = list(self.backend.iter_resources(objs=[BaseAudio], split_path=[key, 'podcasts']))
+                self.assertTrue(len(emissions) > 0)
+                podcasts = list(self.backend.iter_resources(objs=[BaseAudio], split_path=emissions[0].split_path))
+                self.assertTrue(len(podcasts) > 0)
+                podcast = self.backend.get_audio(podcasts[0].id)
+                self.assertTrue(podcast.url)
+
     def test_search_radio(self):
         l = list(self.backend.iter_radios_search('bleu'))
         self.assertTrue(len(l) > 0)