[movingimage] Adapt to the new domain name and fix extraction

Closes #10466

diff --git a/ChangeLog b/ChangeLog
index 0f8076d96d0794d81cf71784f905647b45500280..877e8112e4462a9cc643fa86e71b408d847f023b 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,9 @@
+version <unreleased>
+
+Extractors
+* [movingimage] Fix for the new site name (#10466)
+
+

 version 2016.08.31
 
 Extractors
 version 2016.08.31
 
 Extractors

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index 21efa96b2364d8a79646802843267852a802481b..8d0688f5398f3e438a36787279d33604c0d9ccf8 100644 (file)
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -486,6 +486,7 @@ from .motherless import MotherlessIE
 from .motorsport import MotorsportIE
 from .movieclips import MovieClipsIE
 from .moviezine import MoviezineIE
 from .motorsport import MotorsportIE
 from .movieclips import MovieClipsIE
 from .moviezine import MoviezineIE

+from .movingimage import MovingImageIE

 from .msn import MSNIE
 from .mtv import (
     MTVIE,
 from .msn import MSNIE
 from .mtv import (
     MTVIE,


@@ -806,7 +807,6 @@ from .srgssr import (
     SRGSSRPlayIE,
 )
 from .srmediathek import SRMediathekIE
     SRGSSRPlayIE,
 )
 from .srmediathek import SRMediathekIE

-from .ssa import SSAIE

 from .stanfordoc import StanfordOpenClassroomIE
 from .steam import SteamIE
 from .streamable import StreamableIE
 from .stanfordoc import StanfordOpenClassroomIE
 from .steam import SteamIE
 from .streamable import StreamableIE

diff --git a/youtube_dl/extractor/ssa.py b/youtube_dl/extractor/movingimage.py
similarity index 65%
rename from youtube_dl/extractor/ssa.py
rename to youtube_dl/extractor/movingimage.py
index 54d1843f2200d0cef7fa2e7b192f673d316c5f18..bb789c32edb45e78e9806faaae169af09826135e 100644 (file)
--- a/youtube_dl/extractor/ssa.py
+++ b/youtube_dl/extractor/movingimage.py
@@ -7,22 +7,19 @@ from ..utils import (
 )
 
 
 )
 
 

-class SSAIE(InfoExtractor):
-    _VALID_URL = r'https?://ssa\.nls\.uk/film/(?P<id>\d+)'
+class MovingImageIE(InfoExtractor):
+    _VALID_URL = r'https?://movingimage\.nls\.uk/film/(?P<id>\d+)'

     _TEST = {
     _TEST = {

-        'url': 'http://ssa.nls.uk/film/3561',
+        'url': 'http://movingimage.nls.uk/film/3561',
+        'md5': '4caa05c2b38453e6f862197571a7be2f',

         'info_dict': {
             'id': '3561',
         'info_dict': {
             'id': '3561',

-            'ext': 'flv',
+            'ext': 'mp4',

             'title': 'SHETLAND WOOL',
             'description': 'md5:c5afca6871ad59b4271e7704fe50ab04',
             'duration': 900,
             'thumbnail': 're:^https?://.*\.jpg$',
         },
             'title': 'SHETLAND WOOL',
             'description': 'md5:c5afca6871ad59b4271e7704fe50ab04',
             'duration': 900,
             'thumbnail': 're:^https?://.*\.jpg$',
         },

-        'params': {
-            # rtmp download
-            'skip_download': True,
-        },

     }
 
     def _real_extract(self, url):
     }
 
     def _real_extract(self, url):


@@ -30,10 +27,9 @@ class SSAIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
 
         webpage = self._download_webpage(url, video_id)
 

-        streamer = self._search_regex(
-            r"'streamer'\s*,\S*'(rtmp[^']+)'", webpage, 'streamer')
-        play_path = self._search_regex(
-            r"'file'\s*,\s*'([^']+)'", webpage, 'file').rpartition('.')[0]
+        formats = self._extract_m3u8_formats(
+            self._html_search_regex(r'file\s*:\s*"([^"]+)"', webpage, 'm3u8 manifest URL'),
+            video_id, ext='mp4', entry_protocol='m3u8_native')

 
         def search_field(field_name, fatal=False):
             return self._search_regex(
 
         def search_field(field_name, fatal=False):
             return self._search_regex(


@@ -44,13 +40,11 @@ class SSAIE(InfoExtractor):
         description = unescapeHTML(search_field('Description'))
         duration = parse_duration(search_field('Running time'))
         thumbnail = self._search_regex(
         description = unescapeHTML(search_field('Description'))
         duration = parse_duration(search_field('Running time'))
         thumbnail = self._search_regex(

-            r"'image'\s*,\s*'([^']+)'", webpage, 'thumbnails', fatal=False)
+            r"image\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False)

 
         return {
             'id': video_id,
 
         return {
             'id': video_id,

-            'url': streamer,
-            'play_path': play_path,
-            'ext': 'flv',
+            'formats': formats,

             'title': title,
             'description': description,
             'duration': duration,
             'title': title,
             'description': description,
             'duration': duration,