]> git.bitcoin.ninja Git - youtube-dl/commitdiff
[viewlift] replace SnagFilms extractors
authorremitamine <remitamine@gmail.com>
Fri, 29 Apr 2016 10:14:42 +0000 (11:14 +0100)
committerremitamine <remitamine@gmail.com>
Fri, 29 Apr 2016 10:24:10 +0000 (11:24 +0100)
- add support for other sites that use the same logic
- improve format extraction and sorting

youtube_dl/extractor/extractors.py
youtube_dl/extractor/generic.py
youtube_dl/extractor/snagfilms.py [deleted file]
youtube_dl/extractor/viewlift.py [new file with mode: 0644]

index 3adcd41c4b8884272b7f7e822750388e11a052cc..b1b7f9b42894d3d6487fea9d03508282358ab4db 100644 (file)
@@ -673,10 +673,6 @@ from .smotri import (
     SmotriUserIE,
     SmotriBroadcastIE,
 )
-from .snagfilms import (
-    SnagFilmsIE,
-    SnagFilmsEmbedIE,
-)
 from .snotr import SnotrIE
 from .sohu import SohuIE
 from .soundcloud import (
@@ -879,6 +875,10 @@ from .vidme import (
 )
 from .vidzi import VidziIE
 from .vier import VierIE, VierVideosIE
+from .viewlift import (
+    ViewLiftIE,
+    ViewLiftEmbedIE,
+)
 from .viewster import ViewsterIE
 from .viidea import ViideaIE
 from .vimeo import (
index a95501d86b6874e2775046e142fb81c4469ed2a0..0f1eb7fa64dbf64b32000fd05ea6b65bb8ea502a 100644 (file)
@@ -51,7 +51,7 @@ from .tnaflix import TNAFlixNetworkEmbedIE
 from .vimeo import VimeoIE
 from .dailymotion import DailymotionCloudIE
 from .onionstudios import OnionStudiosIE
-from .snagfilms import SnagFilmsEmbedIE
+from .viewlift import ViewLiftEmbedIE
 from .screenwavemedia import ScreenwaveMediaIE
 from .mtv import MTVServicesEmbeddedIE
 from .pladform import PladformIE
@@ -1924,10 +1924,10 @@ class GenericIE(InfoExtractor):
         if onionstudios_url:
             return self.url_result(onionstudios_url)
 
-        # Look for SnagFilms embeds
-        snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
-        if snagfilms_url:
-            return self.url_result(snagfilms_url)
+        # Look for ViewLift embeds
+        viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
+        if viewlift_url:
+            return self.url_result(viewlift_url)
 
         # Look for JWPlatform embeds
         jwplatform_url = JWPlatformIE._extract_url(webpage)
diff --git a/youtube_dl/extractor/snagfilms.py b/youtube_dl/extractor/snagfilms.py
deleted file mode 100644 (file)
index 6977afb..0000000
+++ /dev/null
@@ -1,181 +0,0 @@
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    clean_html,
-    determine_ext,
-    int_or_none,
-    js_to_json,
-    parse_duration,
-)
-
-
-class SnagFilmsEmbedIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?:www|embed)\.)?snagfilms\.com/embed/player\?.*\bfilmId=(?P<id>[\da-f-]{36})'
-    _TESTS = [{
-        'url': 'http://embed.snagfilms.com/embed/player?filmId=74849a00-85a9-11e1-9660-123139220831&w=500',
-        'md5': '2924e9215c6eff7a55ed35b72276bd93',
-        'info_dict': {
-            'id': '74849a00-85a9-11e1-9660-123139220831',
-            'ext': 'mp4',
-            'title': '#whilewewatch',
-        }
-    }, {
-        # invalid labels, 360p is better that 480p
-        'url': 'http://www.snagfilms.com/embed/player?filmId=17ca0950-a74a-11e0-a92a-0026bb61d036',
-        'md5': '882fca19b9eb27ef865efeeaed376a48',
-        'info_dict': {
-            'id': '17ca0950-a74a-11e0-a92a-0026bb61d036',
-            'ext': 'mp4',
-            'title': 'Life in Limbo',
-        }
-    }, {
-        'url': 'http://www.snagfilms.com/embed/player?filmId=0000014c-de2f-d5d6-abcf-ffef58af0017',
-        'only_matching': True,
-    }]
-
-    @staticmethod
-    def _extract_url(webpage):
-        mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:embed\.)?snagfilms\.com/embed/player.+?)\1',
-            webpage)
-        if mobj:
-            return mobj.group('url')
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        if '>This film is not playable in your area.<' in webpage:
-            raise ExtractorError(
-                'Film %s is not playable in your area.' % video_id, expected=True)
-
-        formats = []
-        for source in self._parse_json(js_to_json(self._search_regex(
-                r'(?s)sources:\s*(\[.+?\]),', webpage, 'json')), video_id):
-            file_ = source.get('file')
-            if not file_:
-                continue
-            type_ = source.get('type')
-            ext = determine_ext(file_)
-            format_id = source.get('label') or ext
-            if all(v == 'm3u8' for v in (type_, ext)):
-                formats.extend(self._extract_m3u8_formats(
-                    file_, video_id, 'mp4', m3u8_id='hls'))
-            else:
-                bitrate = int_or_none(self._search_regex(
-                    [r'(\d+)kbps', r'_\d{1,2}x\d{1,2}_(\d{3,})\.%s' % ext],
-                    file_, 'bitrate', default=None))
-                height = int_or_none(self._search_regex(
-                    r'^(\d+)[pP]$', format_id, 'height', default=None))
-                formats.append({
-                    'url': file_,
-                    'format_id': format_id,
-                    'tbr': bitrate,
-                    'height': height,
-                })
-        self._sort_formats(formats)
-
-        title = self._search_regex(
-            [r"title\s*:\s*'([^']+)'", r'<title>([^<]+)</title>'],
-            webpage, 'title')
-
-        return {
-            'id': video_id,
-            'title': title,
-            'formats': formats,
-        }
-
-
-class SnagFilmsIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?snagfilms\.com/(?:films/title|show)/(?P<id>[^?#]+)'
-    _TESTS = [{
-        'url': 'http://www.snagfilms.com/films/title/lost_for_life',
-        'md5': '19844f897b35af219773fd63bdec2942',
-        'info_dict': {
-            'id': '0000014c-de2f-d5d6-abcf-ffef58af0017',
-            'display_id': 'lost_for_life',
-            'ext': 'mp4',
-            'title': 'Lost for Life',
-            'description': 'md5:fbdacc8bb6b455e464aaf98bc02e1c82',
-            'thumbnail': 're:^https?://.*\.jpg',
-            'duration': 4489,
-            'categories': ['Documentary', 'Crime', 'Award Winning', 'Festivals']
-        }
-    }, {
-        'url': 'http://www.snagfilms.com/show/the_world_cut_project/india',
-        'md5': 'e6292e5b837642bbda82d7f8bf3fbdfd',
-        'info_dict': {
-            'id': '00000145-d75c-d96e-a9c7-ff5c67b20000',
-            'display_id': 'the_world_cut_project/india',
-            'ext': 'mp4',
-            'title': 'India',
-            'description': 'md5:5c168c5a8f4719c146aad2e0dfac6f5f',
-            'thumbnail': 're:^https?://.*\.jpg',
-            'duration': 979,
-            'categories': ['Documentary', 'Sports', 'Politics']
-        }
-    }, {
-        # Film is not playable in your area.
-        'url': 'http://www.snagfilms.com/films/title/inside_mecca',
-        'only_matching': True,
-    }, {
-        # Film is not available.
-        'url': 'http://www.snagfilms.com/show/augie_alone/flirting',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, display_id)
-
-        if ">Sorry, the Film you're looking for is not available.<" in webpage:
-            raise ExtractorError(
-                'Film %s is not available.' % display_id, expected=True)
-
-        film_id = self._search_regex(r'filmId=([\da-f-]{36})"', webpage, 'film id')
-
-        snag = self._parse_json(
-            self._search_regex(
-                'Snag\.page\.data\s*=\s*(\[.+?\]);', webpage, 'snag'),
-            display_id)
-
-        for item in snag:
-            if item.get('data', {}).get('film', {}).get('id') == film_id:
-                data = item['data']['film']
-                title = data['title']
-                description = clean_html(data.get('synopsis'))
-                thumbnail = data.get('image')
-                duration = int_or_none(data.get('duration') or data.get('runtime'))
-                categories = [
-                    category['title'] for category in data.get('categories', [])
-                    if category.get('title')]
-                break
-        else:
-            title = self._search_regex(
-                r'itemprop="title">([^<]+)<', webpage, 'title')
-            description = self._html_search_regex(
-                r'(?s)<div itemprop="description" class="film-synopsis-inner ">(.+?)</div>',
-                webpage, 'description', default=None) or self._og_search_description(webpage)
-            thumbnail = self._og_search_thumbnail(webpage)
-            duration = parse_duration(self._search_regex(
-                r'<span itemprop="duration" class="film-duration strong">([^<]+)<',
-                webpage, 'duration', fatal=False))
-            categories = re.findall(r'<a href="/movies/[^"]+">([^<]+)</a>', webpage)
-
-        return {
-            '_type': 'url_transparent',
-            'url': 'http://embed.snagfilms.com/embed/player?filmId=%s' % film_id,
-            'id': film_id,
-            'display_id': display_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'categories': categories,
-        }
diff --git a/youtube_dl/extractor/viewlift.py b/youtube_dl/extractor/viewlift.py
new file mode 100644 (file)
index 0000000..dd4a13a
--- /dev/null
@@ -0,0 +1,196 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    clean_html,
+    determine_ext,
+    int_or_none,
+    js_to_json,
+    parse_duration,
+)
+
+
+class ViewLiftBaseIE(InfoExtractor):
+    _DOMAINS_REGEX = '(?:snagfilms|snagxtreme|funnyforfree|kiddovid|winnersview|monumentalsportsnetwork|vayafilm)\.com|kesari\.tv'
+
+
+class ViewLiftEmbedIE(ViewLiftBaseIE):
+    _VALID_URL = r'https?://(?:(?:www|embed)\.)?(?:%s)/embed/player\?.*\bfilmId=(?P<id>[\da-f-]{36})' % ViewLiftBaseIE._DOMAINS_REGEX
+    _TESTS = [{
+        'url': 'http://embed.snagfilms.com/embed/player?filmId=74849a00-85a9-11e1-9660-123139220831&w=500',
+        'md5': '2924e9215c6eff7a55ed35b72276bd93',
+        'info_dict': {
+            'id': '74849a00-85a9-11e1-9660-123139220831',
+            'ext': 'mp4',
+            'title': '#whilewewatch',
+        }
+    }, {
+        # invalid labels, 360p is better that 480p
+        'url': 'http://www.snagfilms.com/embed/player?filmId=17ca0950-a74a-11e0-a92a-0026bb61d036',
+        'md5': '882fca19b9eb27ef865efeeaed376a48',
+        'info_dict': {
+            'id': '17ca0950-a74a-11e0-a92a-0026bb61d036',
+            'ext': 'mp4',
+            'title': 'Life in Limbo',
+        }
+    }, {
+        'url': 'http://www.snagfilms.com/embed/player?filmId=0000014c-de2f-d5d6-abcf-ffef58af0017',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:embed\.)?(?:%s)/embed/player.+?)\1' % ViewLiftBaseIE._DOMAINS_REGEX,
+            webpage)
+        if mobj:
+            return mobj.group('url')
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        if '>This film is not playable in your area.<' in webpage:
+            raise ExtractorError(
+                'Film %s is not playable in your area.' % video_id, expected=True)
+
+        formats = []
+        has_bitrate = False
+        for source in self._parse_json(js_to_json(self._search_regex(
+                r'(?s)sources:\s*(\[.+?\]),', webpage, 'json')), video_id):
+            file_ = source.get('file')
+            if not file_:
+                continue
+            type_ = source.get('type')
+            ext = determine_ext(file_)
+            format_id = source.get('label') or ext
+            if all(v == 'm3u8' or v == 'hls' for v in (type_, ext)):
+                formats.extend(self._extract_m3u8_formats(
+                    file_, video_id, 'mp4', m3u8_id='hls'))
+            else:
+                bitrate = int_or_none(self._search_regex(
+                    [r'(\d+)kbps', r'_\d{1,2}x\d{1,2}_(\d{3,})\.%s' % ext],
+                    file_, 'bitrate', default=None))
+                if not has_bitrate and bitrate:
+                    has_bitrate = True
+                height = int_or_none(self._search_regex(
+                    r'^(\d+)[pP]$', format_id, 'height', default=None))
+                formats.append({
+                    'url': file_,
+                    'format_id': 'http-%s%s' % (format_id, ('-%dk' % bitrate if bitrate else '')),
+                    'tbr': bitrate,
+                    'height': height,
+                })
+        field_preference = None if has_bitrate else ('height', 'tbr', 'format_id')
+        self._sort_formats(formats, field_preference)
+
+        title = self._search_regex(
+            [r"title\s*:\s*'([^']+)'", r'<title>([^<]+)</title>'],
+            webpage, 'title')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+        }
+
+
+class ViewLiftIE(ViewLiftBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?(?P<domain>%s)/(?:films/title|show|(?:news/)?videos?)/(?P<id>[^?#]+)' % ViewLiftBaseIE._DOMAINS_REGEX
+    _TESTS = [{
+        'url': 'http://www.snagfilms.com/films/title/lost_for_life',
+        'md5': '19844f897b35af219773fd63bdec2942',
+        'info_dict': {
+            'id': '0000014c-de2f-d5d6-abcf-ffef58af0017',
+            'display_id': 'lost_for_life',
+            'ext': 'mp4',
+            'title': 'Lost for Life',
+            'description': 'md5:fbdacc8bb6b455e464aaf98bc02e1c82',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'duration': 4489,
+            'categories': ['Documentary', 'Crime', 'Award Winning', 'Festivals']
+        }
+    }, {
+        'url': 'http://www.snagfilms.com/show/the_world_cut_project/india',
+        'md5': 'e6292e5b837642bbda82d7f8bf3fbdfd',
+        'info_dict': {
+            'id': '00000145-d75c-d96e-a9c7-ff5c67b20000',
+            'display_id': 'the_world_cut_project/india',
+            'ext': 'mp4',
+            'title': 'India',
+            'description': 'md5:5c168c5a8f4719c146aad2e0dfac6f5f',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'duration': 979,
+            'categories': ['Documentary', 'Sports', 'Politics']
+        }
+    }, {
+        # Film is not playable in your area.
+        'url': 'http://www.snagfilms.com/films/title/inside_mecca',
+        'only_matching': True,
+    }, {
+        # Film is not available.
+        'url': 'http://www.snagfilms.com/show/augie_alone/flirting',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.winnersview.com/videos/the-good-son',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.kesari.tv/news/video/1461919076414',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        domain, display_id = re.match(self._VALID_URL, url).groups()
+
+        webpage = self._download_webpage(url, display_id)
+
+        if ">Sorry, the Film you're looking for is not available.<" in webpage:
+            raise ExtractorError(
+                'Film %s is not available.' % display_id, expected=True)
+
+        film_id = self._search_regex(r'filmId=([\da-f-]{36})"', webpage, 'film id')
+
+        snag = self._parse_json(
+            self._search_regex(
+                'Snag\.page\.data\s*=\s*(\[.+?\]);', webpage, 'snag'),
+            display_id)
+
+        for item in snag:
+            if item.get('data', {}).get('film', {}).get('id') == film_id:
+                data = item['data']['film']
+                title = data['title']
+                description = clean_html(data.get('synopsis'))
+                thumbnail = data.get('image')
+                duration = int_or_none(data.get('duration') or data.get('runtime'))
+                categories = [
+                    category['title'] for category in data.get('categories', [])
+                    if category.get('title')]
+                break
+        else:
+            title = self._search_regex(
+                r'itemprop="title">([^<]+)<', webpage, 'title')
+            description = self._html_search_regex(
+                r'(?s)<div itemprop="description" class="film-synopsis-inner ">(.+?)</div>',
+                webpage, 'description', default=None) or self._og_search_description(webpage)
+            thumbnail = self._og_search_thumbnail(webpage)
+            duration = parse_duration(self._search_regex(
+                r'<span itemprop="duration" class="film-duration strong">([^<]+)<',
+                webpage, 'duration', fatal=False))
+            categories = re.findall(r'<a href="/movies/[^"]+">([^<]+)</a>', webpage)
+
+        return {
+            '_type': 'url_transparent',
+            'url': 'http://%s/embed/player?filmId=%s' % (domain, film_id),
+            'id': film_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'categories': categories,
+            'ie_key': 'ViewLiftEmbed',
+        }