Update upstream source from tag 'upstream/2018.11.07'

[youtubedl] / youtube_dl / extractor / npo.py

diff --git a/youtube_dl/extractor/npo.py b/youtube_dl/extractor/npo.py
index 79296f0ef4bdd3ce172a2c59ffcf59b781abf458..c2cb85a734f256330b9cbb9bfd77910a6f962c45 100644 (file)
--- a/youtube_dl/extractor/npo.py
+++ b/youtube_dl/extractor/npo.py
@@ -11,6 +11,7 @@ from ..utils import (
     determine_ext,
     ExtractorError,
     fix_xml_ampersands,
     determine_ext,
     ExtractorError,
     fix_xml_ampersands,

+    int_or_none,

     orderedSet,
     parse_duration,
     qualities,
     orderedSet,
     parse_duration,
     qualities,


@@ -28,17 +29,17 @@ class NPOBaseIE(InfoExtractor):
 
 class NPOIE(NPOBaseIE):
     IE_NAME = 'npo'
 
 class NPOIE(NPOBaseIE):
     IE_NAME = 'npo'

-    IE_DESC = 'npo.nl and ntr.nl'
+    IE_DESC = 'npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl'

     _VALID_URL = r'''(?x)
                     (?:
                         npo:|
                         https?://
                             (?:www\.)?
                             (?:
     _VALID_URL = r'''(?x)
                     (?:
                         npo:|
                         https?://
                             (?:www\.)?
                             (?:

-                                npo\.nl/(?!live|radio)(?:[^/]+/){2}|
-                                ntr\.nl/(?:[^/]+/){2,}|
+                                npo\.nl/(?:[^/]+/)*|
+                                (?:ntr|npostart)\.nl/(?:[^/]+/){2,}|

                                 omroepwnl\.nl/video/fragment/[^/]+__|
                                 omroepwnl\.nl/video/fragment/[^/]+__|

-                                zapp\.nl/[^/]+/[^/]+/
+                                (?:zapp|npo3)\.nl/(?:[^/]+/){2,}

                             )
                         )
                         (?P<id>[^/?#]+)
                             )
                         )
                         (?P<id>[^/?#]+)


@@ -146,12 +147,33 @@ class NPOIE(NPOBaseIE):
     }, {
         'url': 'http://www.zapp.nl/beste-vrienden-quiz/extra-video-s/WO_NTR_1067990',
         'only_matching': True,
     }, {
         'url': 'http://www.zapp.nl/beste-vrienden-quiz/extra-video-s/WO_NTR_1067990',
         'only_matching': True,

+    }, {
+        'url': 'https://www.npo3.nl/3onderzoekt/16-09-2015/VPWON_1239870',
+        'only_matching': True,

     }, {
         # live stream
         'url': 'npo:LI_NL1_4188102',
         'only_matching': True,
     }, {
         # live stream
         'url': 'npo:LI_NL1_4188102',
         'only_matching': True,

+    }, {
+        'url': 'http://www.npo.nl/radio-gaga/13-06-2017/BNN_101383373',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.zapp.nl/1803-skelterlab/instructie-video-s/740-instructievideo-s/POMS_AT_11736927',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.npostart.nl/broodje-gezond-ei/28-05-2018/KN_1698996',
+        'only_matching': True,
+    }, {
+        'url': 'https://npo.nl/KN_1698996',
+        'only_matching': True,

     }]
 
     }]
 

+    @classmethod
+    def suitable(cls, url):
+        return (False if any(ie.suitable(url)
+                for ie in (NPOLiveIE, NPORadioIE, NPORadioFragmentIE))
+                else super(NPOIE, cls).suitable(url))
+

     def _real_extract(self, url):
         video_id = self._match_id(url)
         return self._get_info(video_id)
     def _real_extract(self, url):
         video_id = self._match_id(url)
         return self._get_info(video_id)


@@ -164,6 +186,10 @@ class NPOIE(NPOBaseIE):
             transform_source=strip_jsonp,
         )
 
             transform_source=strip_jsonp,
         )
 

+        error = metadata.get('error')
+        if error:
+            raise ExtractorError(error, expected=True)
+

         # For some videos actual video id (prid) is different (e.g. for
         # http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698
         # video id is POMS_WNL_853698 but prid is POW_00996502)
         # For some videos actual video id (prid) is different (e.g. for
         # http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698
         # video id is POMS_WNL_853698 but prid is POW_00996502)


@@ -181,7 +207,15 @@ class NPOIE(NPOBaseIE):
         formats = []
         urls = set()
 
         formats = []
         urls = set()
 

-        quality = qualities(['adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std'])
+        def is_legal_url(format_url):
+            return format_url and format_url not in urls and re.match(
+                r'^(?:https?:)?//', format_url)
+
+        QUALITY_LABELS = ('Laag', 'Normaal', 'Hoog')
+        QUALITY_FORMATS = ('adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std')
+
+        quality_from_label = qualities(QUALITY_LABELS)
+        quality_from_format_id = qualities(QUALITY_FORMATS)

         items = self._download_json(
             'http://ida.omroep.nl/app.php/%s' % video_id, video_id,
             'Downloading formats JSON', query={
         items = self._download_json(
             'http://ida.omroep.nl/app.php/%s' % video_id, video_id,
             'Downloading formats JSON', query={


@@ -190,18 +224,34 @@ class NPOIE(NPOBaseIE):
             })['items'][0]
         for num, item in enumerate(items):
             item_url = item.get('url')
             })['items'][0]
         for num, item in enumerate(items):
             item_url = item.get('url')

-            if not item_url or item_url in urls:
+            if not is_legal_url(item_url):

                 continue
             urls.add(item_url)
             format_id = self._search_regex(
                 r'video/ida/([^/]+)', item_url, 'format id',
                 default=None)
 
                 continue
             urls.add(item_url)
             format_id = self._search_regex(
                 r'video/ida/([^/]+)', item_url, 'format id',
                 default=None)
 

+            item_label = item.get('label')
+

             def add_format_url(format_url):
             def add_format_url(format_url):

+                width = int_or_none(self._search_regex(
+                    r'(\d+)[xX]\d+', format_url, 'width', default=None))
+                height = int_or_none(self._search_regex(
+                    r'\d+[xX](\d+)', format_url, 'height', default=None))
+                if item_label in QUALITY_LABELS:
+                    quality = quality_from_label(item_label)
+                    f_id = item_label
+                elif item_label in QUALITY_FORMATS:
+                    quality = quality_from_format_id(format_id)
+                    f_id = format_id
+                else:
+                    quality, f_id = [None] * 2

                 formats.append({
                     'url': format_url,
                 formats.append({
                     'url': format_url,

-                    'format_id': format_id,
-                    'quality': quality(format_id),
+                    'format_id': f_id,
+                    'width': width,
+                    'height': height,
+                    'quality': quality,

                 })
 
             # Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706
                 })
 
             # Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706


@@ -213,7 +263,7 @@ class NPOIE(NPOBaseIE):
                 stream_info = self._download_json(
                     item_url + '&type=json', video_id,
                     'Downloading %s stream JSON'
                 stream_info = self._download_json(
                     item_url + '&type=json', video_id,
                     'Downloading %s stream JSON'

-                    % item.get('label') or item.get('format') or format_id or num)
+                    % item_label or item.get('format') or format_id or num)

             except ExtractorError as ee:
                 if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
                     error = (self._parse_json(
             except ExtractorError as ee:
                 if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
                     error = (self._parse_json(


@@ -232,7 +282,7 @@ class NPOIE(NPOBaseIE):
                 video_url = stream_info.get('url')
             if not video_url or video_url in urls:
                 continue
                 video_url = stream_info.get('url')
             if not video_url or video_url in urls:
                 continue

-            urls.add(item_url)
+            urls.add(video_url)

             if determine_ext(video_url) == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(
                     video_url, video_id, ext='mp4',
             if determine_ext(video_url) == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(
                     video_url, video_id, ext='mp4',


@@ -245,7 +295,7 @@ class NPOIE(NPOBaseIE):
         if not is_live:
             for num, stream in enumerate(metadata.get('streams', [])):
                 stream_url = stream.get('url')
         if not is_live:
             for num, stream in enumerate(metadata.get('streams', [])):
                 stream_url = stream.get('url')

-                if not stream_url or stream_url in urls:
+                if not is_legal_url(stream_url):

                     continue
                 urls.add(stream_url)
                 # smooth streaming is not supported
                     continue
                 urls.add(stream_url)
                 # smooth streaming is not supported


@@ -338,7 +388,7 @@ class NPOLiveIE(NPOBaseIE):
         webpage = self._download_webpage(url, display_id)
 
         live_id = self._search_regex(
         webpage = self._download_webpage(url, display_id)
 
         live_id = self._search_regex(

-            r'data-prid="([^"]+)"', webpage, 'live id')
+            [r'media-id="([^"]+)"', r'data-prid="([^"]+)"'], webpage, 'live id')

 
         return {
             '_type': 'url_transparent',
 
         return {
             '_type': 'url_transparent',


@@ -351,7 +401,7 @@ class NPOLiveIE(NPOBaseIE):
 
 class NPORadioIE(InfoExtractor):
     IE_NAME = 'npo.nl:radio'
 
 class NPORadioIE(InfoExtractor):
     IE_NAME = 'npo.nl:radio'

-    _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P<id>[^/]+)/?$'
+    _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P<id>[^/]+)'

 
     _TEST = {
         'url': 'http://www.npo.nl/radio/radio-1',
 
     _TEST = {
         'url': 'http://www.npo.nl/radio/radio-1',


@@ -366,6 +416,10 @@ class NPORadioIE(InfoExtractor):
         }
     }
 
         }
     }
 

+    @classmethod
+    def suitable(cls, url):
+        return False if NPORadioFragmentIE.suitable(url) else super(NPORadioIE, cls).suitable(url)
+

     @staticmethod
     def _html_get_attribute_regex(attribute):
         return r'{0}\s*=\s*\'([^\']+)\''.format(attribute)
     @staticmethod
     def _html_get_attribute_regex(attribute):
         return r'{0}\s*=\s*\'([^\']+)\''.format(attribute)


@@ -463,7 +517,7 @@ class SchoolTVIE(NPODataMidEmbedIE):
 
 class HetKlokhuisIE(NPODataMidEmbedIE):
     IE_NAME = 'hetklokhuis'
 
 class HetKlokhuisIE(NPODataMidEmbedIE):
     IE_NAME = 'hetklokhuis'

-    _VALID_URL = r'https?://(?:www\.)?hetklokhuis.nl/[^/]+/\d+/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?hetklokhuis\.nl/[^/]+/\d+/(?P<id>[^/?#&]+)'

 
     _TEST = {
         'url': 'http://hetklokhuis.nl/tv-uitzending/3471/Zwaartekrachtsgolven',
 
     _TEST = {
         'url': 'http://hetklokhuis.nl/tv-uitzending/3471/Zwaartekrachtsgolven',