From 34e48bed3b562ef32c3bfa14ba59101786316464 Mon Sep 17 00:00:00 2001 From: dinesh Date: Fri, 24 Oct 2014 02:41:10 +0530 Subject: [PATCH 1/4] [extractor/common] Added support for f4m manifest Version 2.0 --- youtube_dl/extractor/common.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index e8366f7f9..290df1175 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -648,6 +648,8 @@ class InfoExtractor(object): formats = [] media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media') + if not media_nodes: + media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media') for i, media_el in enumerate(media_nodes): tbr = int_or_none(media_el.attrib.get('bitrate')) format_id = 'f4m-%d' % (i if tbr is None else tbr) From 7a47d07c6dbc8b6bb3be321af886c1774d68e0d6 Mon Sep 17 00:00:00 2001 From: dinesh Date: Fri, 24 Oct 2014 09:47:39 +0530 Subject: [PATCH 2/4] [extractor/common] href attribute added --- youtube_dl/extractor/common.py | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 290df1175..a8674dd85 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -647,10 +647,14 @@ class InfoExtractor(object): 'Unable to download f4m manifest') formats = [] + manifest_version = '1.0' media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media') if not media_nodes: + manifest_version = '2.0' media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media') for i, media_el in enumerate(media_nodes): + if manifest_version == '2.0': + manifest_url = '/'.join(manifest_url.split('/')[:-1]) + '/' + media_el.attrib.get('href') tbr = int_or_none(media_el.attrib.get('bitrate')) format_id = 'f4m-%d' % (i if tbr is None else tbr) formats.append({ From 25fadd06d078d54e30e187063d8b45fae31bed81 Mon Sep 17 00:00:00 2001 From: dinesh Date: Fri, 24 Oct 2014 09:49:01 +0530 Subject: [PATCH 3/4] [Rte] New extractor added --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/rte.py | 53 ++++++++++++++++++++++++++++++++ 2 files changed, 54 insertions(+) create mode 100644 youtube_dl/extractor/rte.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 0de0b4587..7918f9ab7 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -297,6 +297,7 @@ from .ro220 import Ro220IE from .rottentomatoes import RottenTomatoesIE from .roxwel import RoxwelIE from .rtbf import RTBFIE +from .rte import RteIE from .rtlnl import RtlXlIE from .rtlnow import RTLnowIE from .rts import RTSIE diff --git a/youtube_dl/extractor/rte.py b/youtube_dl/extractor/rte.py new file mode 100644 index 000000000..ab12bb5fd --- /dev/null +++ b/youtube_dl/extractor/rte.py @@ -0,0 +1,53 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + +from ..utils import ( + float_or_none, +) + + +class RteIE(InfoExtractor): + _VALID_URL = r'http?://(?:www\.)?rte\.ie/player/in/show/(?P[0-9]+)/' + _TEST = { + 'url': 'http://www.rte.ie/player/in/show/10336191/', + 'info_dict': { + 'id': '10336191', + 'ext': 'mp4', + 'title': 'Nine News', + 'thumbnail': 're:^https?://.*\.jpg$', + 'description': 'The One O\'Clock News followed by Weather.', + 'duration': 1622963.0, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + title = self._og_search_title(webpage) + + description = self._search_regex(r'', webpage, 'description') + duration = float_or_none(self._html_search_meta('duration', webpage, 'duration')) + + thumbnail_id = self._search_regex(r'', webpage, 'thumbnail') + thumbnail = 'http://img.rasset.ie/' + thumbnail_id + '.jpg' + + feeds_url = self._html_search_meta("feeds-prefix", webpage, 'feeds url') + video_id + json_string = self._download_json(feeds_url, video_id) + + # f4m_url = server + relative_url + f4m_url = json_string['shows'][0]['media:group'][0]['rte:server'] + json_string['shows'][0]['media:group'][0]['url'] + f4m_formats = self._extract_f4m_formats(f4m_url, video_id) + for f in f4m_formats: + del f['tbr'] + + return { + 'id': video_id, + 'title': title, + 'formats': f4m_formats, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + } \ No newline at end of file From 0551a02b82b4209422e0734150e0186210cd0723 Mon Sep 17 00:00:00 2001 From: dinesh Date: Mon, 27 Oct 2014 01:08:51 +0530 Subject: [PATCH 4/4] [Rte] Improve extractor --- youtube_dl/extractor/rte.py | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/rte.py b/youtube_dl/extractor/rte.py index ab12bb5fd..8d4e94e55 100644 --- a/youtube_dl/extractor/rte.py +++ b/youtube_dl/extractor/rte.py @@ -18,7 +18,7 @@ class RteIE(InfoExtractor): 'title': 'Nine News', 'thumbnail': 're:^https?://.*\.jpg$', 'description': 'The One O\'Clock News followed by Weather.', - 'duration': 1622963.0, + 'duration': 1622.963, } } @@ -29,7 +29,7 @@ class RteIE(InfoExtractor): title = self._og_search_title(webpage) description = self._search_regex(r'', webpage, 'description') - duration = float_or_none(self._html_search_meta('duration', webpage, 'duration')) + duration = float_or_none(self._html_search_meta('duration', webpage, 'duration'), 1000) thumbnail_id = self._search_regex(r'', webpage, 'thumbnail') thumbnail = 'http://img.rasset.ie/' + thumbnail_id + '.jpg' @@ -40,8 +40,13 @@ class RteIE(InfoExtractor): # f4m_url = server + relative_url f4m_url = json_string['shows'][0]['media:group'][0]['rte:server'] + json_string['shows'][0]['media:group'][0]['url'] f4m_formats = self._extract_f4m_formats(f4m_url, video_id) - for f in f4m_formats: - del f['tbr'] + f4m_formats = [{ + 'format_id': f['format_id'], + 'url': f['url'], + 'ext': 'mp4', + 'width': f['width'], + 'height': f['height'], + } for f in f4m_formats ] return { 'id': video_id,