aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/ceskatelevize.py45
-rw-r--r--youtube_dl/extractor/nrk.py132
2 files changed, 152 insertions, 25 deletions
diff --git a/youtube_dl/extractor/ceskatelevize.py b/youtube_dl/extractor/ceskatelevize.py
index ba8376338..f70e090bb 100644
--- a/youtube_dl/extractor/ceskatelevize.py
+++ b/youtube_dl/extractor/ceskatelevize.py
@@ -3,7 +3,7 @@ from __future__ import unicode_literals
import re
-from .common import InfoExtractor
+from .subtitles import SubtitlesInfoExtractor
from ..compat import (
compat_urllib_request,
compat_urllib_parse,
@@ -15,7 +15,7 @@ from ..utils import (
)
-class CeskaTelevizeIE(InfoExtractor):
+class CeskaTelevizeIE(SubtitlesInfoExtractor):
_VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(.+/)?(?P<id>[^?#]+)'
_TESTS = [
@@ -104,6 +104,17 @@ class CeskaTelevizeIE(InfoExtractor):
duration = float_or_none(item.get('duration'))
thumbnail = item.get('previewImageUrl')
+ subtitles = {}
+ subs = item.get('subtitles')
+ if subs:
+ subtitles['cs'] = subs[0]['url']
+
+ if self._downloader.params.get('listsubtitles', False):
+ self._list_available_subtitles(video_id, subtitles)
+ return
+
+ subtitles = self._fix_subtitles(self.extract_subtitles(video_id, subtitles))
+
return {
'id': episode_id,
'title': title,
@@ -111,4 +122,34 @@ class CeskaTelevizeIE(InfoExtractor):
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
+ 'subtitles': subtitles,
}
+
+ @staticmethod
+ def _fix_subtitles(subtitles):
+ """ Convert millisecond-based subtitles to SRT """
+ if subtitles is None:
+ return subtitles # subtitles not requested
+
+ def _msectotimecode(msec):
+ """ Helper utility to convert milliseconds to timecode """
+ components = []
+ for divider in [1000, 60, 60, 100]:
+ components.append(msec % divider)
+ msec //= divider
+ return "{3:02}:{2:02}:{1:02},{0:03}".format(*components)
+
+ def _fix_subtitle(subtitle):
+ for line in subtitle.splitlines():
+ m = re.match(r"^\s*([0-9]+);\s*([0-9]+)\s+([0-9]+)\s*$", line)
+ if m:
+ yield m.group(1)
+ start, stop = (_msectotimecode(int(t)) for t in m.groups()[1:])
+ yield "{0} --> {1}".format(start, stop)
+ else:
+ yield line
+
+ fixed_subtitles = {}
+ for k, v in subtitles.items():
+ fixed_subtitles[k] = "\r\n".join(_fix_subtitle(v))
+ return fixed_subtitles
diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py
index 43e8e619f..e950c76dd 100644
--- a/youtube_dl/extractor/nrk.py
+++ b/youtube_dl/extractor/nrk.py
@@ -72,7 +72,7 @@ class NRKIE(InfoExtractor):
class NRKTVIE(InfoExtractor):
- _VALID_URL = r'http://tv\.nrk(?:super)?\.no/(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})'
+ _VALID_URL = r'http://tv\.nrk(?:super)?\.no/(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?'
_TESTS = [
{
@@ -85,7 +85,7 @@ class NRKTVIE(InfoExtractor):
'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
'upload_date': '20140523',
'duration': 1741.52,
- }
+ },
},
{
'url': 'http://tv.nrk.no/program/mdfp15000514',
@@ -97,39 +97,125 @@ class NRKTVIE(InfoExtractor):
'description': 'md5:654c12511f035aed1e42bdf5db3b206a',
'upload_date': '20140524',
'duration': 4605.0,
- }
+ },
},
+ {
+ # single playlist video
+ 'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
+ 'md5': 'adbd1dbd813edaf532b0a253780719c2',
+ 'info_dict': {
+ 'id': 'MSPO40010515-part2',
+ 'ext': 'flv',
+ 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
+ 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
+ 'upload_date': '20150106',
+ },
+ 'skip': 'Only works from Norway',
+ 'params': {
+ 'proxy': '127.0.0.1:8118',
+ },
+ },
+ {
+ 'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
+ 'playlist': [
+ {
+ 'md5': '9480285eff92d64f06e02a5367970a7a',
+ 'info_dict': {
+ 'id': 'MSPO40010515-part1',
+ 'ext': 'flv',
+ 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 1:2)',
+ 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
+ 'upload_date': '20150106',
+ },
+ },
+ {
+ 'md5': 'adbd1dbd813edaf532b0a253780719c2',
+ 'info_dict': {
+ 'id': 'MSPO40010515-part2',
+ 'ext': 'flv',
+ 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
+ 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
+ 'upload_date': '20150106',
+ },
+ },
+ ],
+ 'info_dict': {
+ 'id': 'MSPO40010515',
+ 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn',
+ 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
+ 'upload_date': '20150106',
+ 'duration': 6947.5199999999995,
+ },
+ 'skip': 'Only works from Norway',
+ 'params': {
+ 'proxy': '127.0.0.1:8118',
+ },
+ }
]
+ def _extract_f4m(self, manifest_url, video_id):
+ return self._extract_f4m_formats(manifest_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', video_id)
+
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
-
- page = self._download_webpage(url, video_id)
-
- title = self._html_search_meta('title', page, 'title')
- description = self._html_search_meta('description', page, 'description')
- thumbnail = self._html_search_regex(r'data-posterimage="([^"]+)"', page, 'thumbnail', fatal=False)
- upload_date = unified_strdate(self._html_search_meta('rightsfrom', page, 'upload date', fatal=False))
- duration = float_or_none(
- self._html_search_regex(r'data-duration="([^"]+)"', page, 'duration', fatal=False))
+ part_id = mobj.group('part_id')
+
+ webpage = self._download_webpage(url, video_id)
+
+ title = self._html_search_meta(
+ 'title', webpage, 'title')
+ description = self._html_search_meta(
+ 'description', webpage, 'description')
+
+ thumbnail = self._html_search_regex(
+ r'data-posterimage="([^"]+)"',
+ webpage, 'thumbnail', fatal=False)
+ upload_date = unified_strdate(self._html_search_meta(
+ 'rightsfrom', webpage, 'upload date', fatal=False))
+ duration = float_or_none(self._html_search_regex(
+ r'data-duration="([^"]+)"',
+ webpage, 'duration', fatal=False))
+
+ # playlist
+ parts = re.findall(
+ r'<a href="#del=(\d+)"[^>]+data-argument="([^"]+)">([^<]+)</a>', webpage)
+ if parts:
+ entries = []
+ for current_part_id, stream_url, part_title in parts:
+ if part_id and current_part_id != part_id:
+ continue
+ video_part_id = '%s-part%s' % (video_id, current_part_id)
+ formats = self._extract_f4m(stream_url, video_part_id)
+ entries.append({
+ 'id': video_part_id,
+ 'title': part_title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'upload_date': upload_date,
+ 'formats': formats,
+ })
+ if part_id:
+ if entries:
+ return entries[0]
+ else:
+ playlist = self.playlist_result(entries, video_id, title, description)
+ playlist.update({
+ 'thumbnail': thumbnail,
+ 'upload_date': upload_date,
+ 'duration': duration,
+ })
+ return playlist
formats = []
- f4m_url = re.search(r'data-media="([^"]+)"', page)
+ f4m_url = re.search(r'data-media="([^"]+)"', webpage)
if f4m_url:
- formats.append({
- 'url': f4m_url.group(1) + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124',
- 'format_id': 'f4m',
- 'ext': 'flv',
- })
+ formats.extend(self._extract_f4m(f4m_url.group(1), video_id))
- m3u8_url = re.search(r'data-hls-media="([^"]+)"', page)
+ m3u8_url = re.search(r'data-hls-media="([^"]+)"', webpage)
if m3u8_url:
- formats.append({
- 'url': m3u8_url.group(1),
- 'format_id': 'm3u8',
- })
+ formats.extend(self._extract_m3u8_formats(m3u8_url.group(1), video_id, 'mp4'))
self._sort_formats(formats)
generated by cgit v1.2.3 (git 2.26.2) at 2025-04-04 20:30:53 +0000