Merge branch 'master' into NBC-issue-13873

2017-09-14 17:27:05 -05:00 · 2017-09-14 17:27:05 -05:00 · 06e590685b
commit 06e590685b
parent 064d515dfe c46680fb2a
5 changed files with 156 additions and 30 deletions
--- a/youtube_dl/downloader/fragment.py
+++ b/youtube_dl/downloader/fragment.py
@ -151,10 +151,15 @@ class FragmentFD(FileDownloader):
        if self.__do_ytdl_file(ctx):
            if os.path.isfile(encodeFilename(self.ytdl_filename(ctx['filename']))):
                self._read_ytdl_file(ctx)
+                if ctx['fragment_index'] > 0 and resume_len == 0:
+                    self.report_error(
+                        'Inconsistent state of incomplete fragment download. '
+                        'Restarting from the beginning...')
+                    ctx['fragment_index'] = resume_len = 0
+                    self._write_ytdl_file(ctx)
            else:
                self._write_ytdl_file(ctx)
-            if ctx['fragment_index'] > 0:
-                assert resume_len > 0
+                assert ctx['fragment_index'] == 0

        dest_stream, tmpfilename = sanitize_open(tmpfilename, open_mode)

--- a/youtube_dl/extractor/condenast.py
+++ b/youtube_dl/extractor/condenast.py
@ -116,16 +116,16 @@ class CondeNastIE(InfoExtractor):
        entries = [self.url_result(build_url(path), 'CondeNast') for path in paths]
        return self.playlist_result(entries, playlist_title=title)

-    def _extract_video_params(self, webpage):
-        query = {}
-        params = self._search_regex(
-            r'(?s)var params = {(.+?)}[;,]', webpage, 'player params', default=None)
-        if params:
-            query.update({
-                'videoId': self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, 'video id'),
-                'playerId': self._search_regex(r'playerId: [\'"](.+?)[\'"]', params, 'player id'),
-                'target': self._search_regex(r'target: [\'"](.+?)[\'"]', params, 'target'),
-            })
+    def _extract_video_params(self, webpage, display_id):
+        query = self._parse_json(
+            self._search_regex(
+                r'(?s)var\s+params\s*=\s*({.+?})[;,]', webpage, 'player params',
+                default='{}'),
+            display_id, transform_source=js_to_json, fatal=False)
+        if query:
+            query['videoId'] = self._search_regex(
+                r'(?:data-video-id=|currentVideoId\s*=\s*)["\']([\da-f]+)',
+                webpage, 'video id', default=None)
        else:
            params = extract_attributes(self._search_regex(
                r'(<[^>]+data-js="video-player"[^>]+>)',
@ -141,17 +141,27 @@ class CondeNastIE(InfoExtractor):
        video_id = params['videoId']

        video_info = None
-        if params.get('playerId'):
-            info_page = self._download_json(
-                'http://player.cnevids.com/player/video.js',
-                video_id, 'Downloading video info', fatal=False, query=params)
-            if info_page:
-                video_info = info_page.get('video')
-            if not video_info:
-                info_page = self._download_webpage(
-                    'http://player.cnevids.com/player/loader.js',
-                    video_id, 'Downloading loader info', query=params)
-        else:
+
+        # New API path
+        query = params.copy()
+        query['embedType'] = 'inline'
+        info_page = self._download_json(
+            'http://player.cnevids.com/embed-api.json', video_id,
+            'Downloading embed info', fatal=False, query=query)
+
+        # Old fallbacks
+        if not info_page:
+            if params.get('playerId'):
+                info_page = self._download_json(
+                    'http://player.cnevids.com/player/video.js', video_id,
+                    'Downloading video info', fatal=False, query=params)
+        if info_page:
+            video_info = info_page.get('video')
+        if not video_info:
+            info_page = self._download_webpage(
+                'http://player.cnevids.com/player/loader.js',
+                video_id, 'Downloading loader info', query=params)
+        if not video_info:
            info_page = self._download_webpage(
                'https://player.cnevids.com/inline/video/%s.js' % video_id,
                video_id, 'Downloading inline info', query={
@ -215,7 +225,7 @@ class CondeNastIE(InfoExtractor):
        if url_type == 'series':
            return self._extract_series(url, webpage)
        else:
-            params = self._extract_video_params(webpage)
+            params = self._extract_video_params(webpage, display_id)
            info = self._search_json_ld(
                webpage, display_id, fatal=False)
            info.update(self._extract_video(params))
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@ -768,6 +768,7 @@ from .ora import OraTVIE
 from .orf import (
    ORFTVthekIE,
    ORFFM4IE,
+    ORFFM4StoryIE,
    ORFOE1IE,
    ORFIPTVIE,
 )
--- a/youtube_dl/extractor/orf.py
+++ b/youtube_dl/extractor/orf.py
@ -6,14 +6,15 @@ import re
 from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
-    HEADRequest,
-    unified_strdate,
-    strip_jsonp,
-    int_or_none,
-    float_or_none,
    determine_ext,
+    float_or_none,
+    HEADRequest,
+    int_or_none,
+    orderedSet,
    remove_end,
+    strip_jsonp,
    unescapeHTML,
+    unified_strdate,
 )


@ -307,3 +308,108 @@ class ORFIPTVIE(InfoExtractor):
            'upload_date': upload_date,
            'formats': formats,
        }
+
+
+class ORFFM4StoryIE(InfoExtractor):
+    IE_NAME = 'orf:fm4:story'
+    IE_DESC = 'fm4.orf.at stories'
+    _VALID_URL = r'https?://fm4\.orf\.at/stories/(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://fm4.orf.at/stories/2865738/',
+        'playlist': [{
+            'md5': 'e1c2c706c45c7b34cf478bbf409907ca',
+            'info_dict': {
+                'id': '547792',
+                'ext': 'flv',
+                'title': 'Manu Delago und Inner Tongue live',
+                'description': 'Manu Delago und Inner Tongue haben bei der FM4 Soundpark Session live alles gegeben. Hier gibt es Fotos und die gesamte Session als Video.',
+                'duration': 1748.52,
+                'thumbnail': r're:^https?://.*\.jpg$',
+                'upload_date': '20170913',
+            },
+        }, {
+            'md5': 'c6dd2179731f86f4f55a7b49899d515f',
+            'info_dict': {
+                'id': '547798',
+                'ext': 'flv',
+                'title': 'Manu Delago und Inner Tongue live (2)',
+                'duration': 1504.08,
+                'thumbnail': r're:^https?://.*\.jpg$',
+                'upload_date': '20170913',
+                'description': 'Manu Delago und Inner Tongue haben bei der FM4 Soundpark Session live alles gegeben. Hier gibt es Fotos und die gesamte Session als Video.',
+            },
+        }],
+    }
+
+    def _real_extract(self, url):
+        story_id = self._match_id(url)
+        webpage = self._download_webpage(url, story_id)
+
+        entries = []
+        all_ids = orderedSet(re.findall(r'data-video(?:id)?="(\d+)"', webpage))
+        for idx, video_id in enumerate(all_ids):
+            data = self._download_json(
+                'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id,
+                video_id)[0]
+
+            duration = float_or_none(data['duration'], 1000)
+
+            video = data['sources']['q8c']
+            load_balancer_url = video['loadBalancerUrl']
+            abr = int_or_none(video.get('audioBitrate'))
+            vbr = int_or_none(video.get('bitrate'))
+            fps = int_or_none(video.get('videoFps'))
+            width = int_or_none(video.get('videoWidth'))
+            height = int_or_none(video.get('videoHeight'))
+            thumbnail = video.get('preview')
+
+            rendition = self._download_json(
+                load_balancer_url, video_id, transform_source=strip_jsonp)
+
+            f = {
+                'abr': abr,
+                'vbr': vbr,
+                'fps': fps,
+                'width': width,
+                'height': height,
+            }
+
+            formats = []
+            for format_id, format_url in rendition['redirect'].items():
+                if format_id == 'rtmp':
+                    ff = f.copy()
+                    ff.update({
+                        'url': format_url,
+                        'format_id': format_id,
+                    })
+                    formats.append(ff)
+                elif determine_ext(format_url) == 'f4m':
+                    formats.extend(self._extract_f4m_formats(
+                        format_url, video_id, f4m_id=format_id))
+                elif determine_ext(format_url) == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        format_url, video_id, 'mp4', m3u8_id=format_id))
+                else:
+                    continue
+            self._sort_formats(formats)
+
+            title = remove_end(self._og_search_title(webpage), ' - fm4.ORF.at')
+            if idx >= 1:
+                # Titles are duplicates, make them unique
+                title += ' (' + str(idx + 1) + ')'
+            description = self._og_search_description(webpage)
+            upload_date = unified_strdate(self._html_search_meta(
+                'dc.date', webpage, 'upload date'))
+
+            entries.append({
+                'id': video_id,
+                'title': title,
+                'description': description,
+                'duration': duration,
+                'thumbnail': thumbnail,
+                'upload_date': upload_date,
+                'formats': formats,
+            })
+
+        return self.playlist_result(entries)
--- a/youtube_dl/extractor/tv4.py
+++ b/youtube_dl/extractor/tv4.py
@ -18,7 +18,7 @@ class TV4IE(InfoExtractor):
            tv4\.se/(?:[^/]+)/klipp/(?:.*)-|
            tv4play\.se/
            (?:
-                (?:program|barn)/(?:[^\?]+)\?video_id=|
+                (?:program|barn)/(?:[^/]+/|(?:[^\?]+)\?video_id=)|
                iframe/video/|
                film/|
                sport/|
@ -63,6 +63,10 @@ class TV4IE(InfoExtractor):
            'url': 'http://www.tv4play.se/barn/looney-tunes?video_id=3062412',
            'only_matching': True,
        },
+        {
+            'url': 'http://www.tv4play.se/program/farang/3922081',
+            'only_matching': True,
+        }
    ]

    def _real_extract(self, url):