aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/puls4.py97
-rw-r--r--youtube_dl/extractor/svtplay.py42
2 files changed, 96 insertions, 43 deletions
diff --git a/youtube_dl/extractor/puls4.py b/youtube_dl/extractor/puls4.py
index 70dedbff3..cce84b9e4 100644
--- a/youtube_dl/extractor/puls4.py
+++ b/youtube_dl/extractor/puls4.py
@@ -1,61 +1,88 @@
# -*- coding: utf-8 -*-
-
from __future__ import unicode_literals
from .common import InfoExtractor
-
-import re
+from ..utils import (
+ ExtractorError,
+ unified_strdate,
+ int_or_none,
+)
class Puls4IE(InfoExtractor):
-
- _VALID_URL = r'https?://www.puls4.com/video/.+?/play/(?P<id>[0-9]+)'
+ _VALID_URL = r'https?://(?:www\.)?puls4\.com/video/[^/]+/play/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'http://www.puls4.com/video/pro-und-contra/play/2716816',
'md5': '49f6a6629747eeec43cef6a46b5df81d',
'info_dict': {
'id': '2716816',
'ext': 'mp4',
- 'title': 'Pro und Contra vom 23.02.2015'}},
- {
+ 'title': 'Pro und Contra vom 23.02.2015',
+ 'description': 'md5:293e44634d9477a67122489994675db6',
+ 'duration': 2989,
+ 'upload_date': '20150224',
+ 'uploader': 'PULS_4',
+ },
+ 'skip': 'Only works from Germany',
+ }, {
'url': 'http://www.puls4.com/video/kult-spielfilme/play/1298106',
'md5': '6a48316c8903ece8dab9b9a7bf7a59ec',
'info_dict': {
'id': '1298106',
'ext': 'mp4',
- 'title': 'Lucky Fritz'}}
- ]
+ 'title': 'Lucky Fritz',
+ },
+ 'skip': 'Only works from Germany',
+ }]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
- # if fsk-button
- real_url = self._html_search_regex(r'\"fsk-button\".+?href=\"([^"]+)',
- webpage, 'fsk_button', default=None)
+ error_message = self._html_search_regex(
+ r'<div class="message-error">(.+?)</div>',
+ webpage, 'error message', default=None)
+ if error_message:
+ raise ExtractorError(
+ '%s returned error: %s' % (self.IE_NAME, error_message), expected=True)
+
+ real_url = self._html_search_regex(
+ r'\"fsk-button\".+?href=\"([^"]+)',
+ webpage, 'fsk_button', default=None)
if real_url:
webpage = self._download_webpage(real_url, video_id)
- title = self._html_search_regex(
- r'<div id="bg_brandableContent">.+?<h1>(.+?)</h1>',
- webpage, 'title', flags=re.DOTALL)
-
- sd_url = self._html_search_regex(
- r'{\"url\":\"([^"]+?)\",\"hd\":false',
- webpage, 'sd_url').replace('\\', '')
-
- formats = [{'format_id': 'sd', 'url': sd_url, 'quality': -2}]
-
- hd_url = self._html_search_regex(
- r'{\"url\":\"([^"]+?)\",\"hd\":true',
- webpage, 'hd_url', default=None)
- if hd_url:
- hd_url = hd_url.replace('\\', '')
- formats.append({'format_id': 'hd', 'url': hd_url, 'quality': -1})
-
- return {
- 'id': video_id,
- 'title': title,
- 'formats': formats,
- 'ext': 'mp4'
- }
+ player = self._search_regex(
+ r'p4_video_player(?:_iframe)?\("video_\d+_container"\s*,(.+?)\);\s*\}',
+ webpage, 'player')
+
+ player_json = self._parse_json(
+ '[%s]' % player, video_id,
+ transform_source=lambda s: s.replace('undefined,', ''))
+
+ formats = None
+ result = None
+
+ for v in player_json:
+ if isinstance(v, list) and not formats:
+ formats = [{
+ 'url': f['url'],
+ 'format': 'hd' if f.get('hd') else 'sd',
+ 'width': int_or_none(f.get('size_x')),
+ 'height': int_or_none(f.get('size_y')),
+ 'tbr': int_or_none(f.get('bitrate')),
+ } for f in v]
+ self._sort_formats(formats)
+ elif isinstance(v, dict) and not result:
+ result = {
+ 'id': video_id,
+ 'title': v['videopartname'].strip(),
+ 'description': v.get('videotitle'),
+ 'duration': int_or_none(v.get('videoduration') or v.get('episodeduration')),
+ 'upload_date': unified_strdate(v.get('clipreleasetime')),
+ 'uploader': v.get('channel'),
+ }
+
+ result['formats'] = formats
+
+ return result
diff --git a/youtube_dl/extractor/svtplay.py b/youtube_dl/extractor/svtplay.py
index eadb9ccb4..433dfd1cb 100644
--- a/youtube_dl/extractor/svtplay.py
+++ b/youtube_dl/extractor/svtplay.py
@@ -1,6 +1,8 @@
# coding: utf-8
from __future__ import unicode_literals
+import re
+
from .common import InfoExtractor
from ..utils import (
determine_ext,
@@ -8,23 +10,40 @@ from ..utils import (
class SVTPlayIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?svtplay\.se/video/(?P<id>[0-9]+)'
- _TEST = {
+ IE_DESC = 'SVT Play and Öppet arkiv'
+ _VALID_URL = r'https?://(?:www\.)?(?P<host>svtplay|oppetarkiv)\.se/video/(?P<id>[0-9]+)'
+ _TESTS = [{
'url': 'http://www.svtplay.se/video/2609989/sm-veckan/sm-veckan-rally-final-sasong-1-sm-veckan-rally-final',
- 'md5': 'f4a184968bc9c802a9b41316657aaa80',
+ 'md5': 'ade3def0643fa1c40587a422f98edfd9',
'info_dict': {
'id': '2609989',
- 'ext': 'mp4',
+ 'ext': 'flv',
'title': 'SM veckan vinter, Örebro - Rally, final',
'duration': 4500,
'thumbnail': 're:^https?://.*[\.-]jpg$',
+ 'age_limit': 0,
},
- }
+ }, {
+ 'url': 'http://www.oppetarkiv.se/video/1058509/rederiet-sasong-1-avsnitt-1-av-318',
+ 'md5': 'c3101a17ce9634f4c1f9800f0746c187',
+ 'info_dict': {
+ 'id': '1058509',
+ 'ext': 'flv',
+ 'title': 'Farlig kryssning',
+ 'duration': 2566,
+ 'thumbnail': 're:^https?://.*[\.-]jpg$',
+ 'age_limit': 0,
+ },
+ 'skip': 'Only works from Sweden',
+ }]
def _real_extract(self, url):
- video_id = self._match_id(url)
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ host = mobj.group('host')
+
info = self._download_json(
- 'http://www.svtplay.se/video/%s?output=json' % video_id, video_id)
+ 'http://www.%s.se/video/%s?output=json' % (host, video_id), video_id)
title = info['context']['title']
thumbnail = info['context'].get('thumbnailImage')
@@ -33,11 +52,16 @@ class SVTPlayIE(InfoExtractor):
formats = []
for vr in video_info['videoReferences']:
vurl = vr['url']
- if determine_ext(vurl) == 'm3u8':
+ ext = determine_ext(vurl)
+ if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
vurl, video_id,
ext='mp4', entry_protocol='m3u8_native',
m3u8_id=vr.get('playerType')))
+ elif ext == 'f4m':
+ formats.extend(self._extract_f4m_formats(
+ vurl + '?hdcore=3.3.0', video_id,
+ f4m_id=vr.get('playerType')))
else:
formats.append({
'format_id': vr.get('playerType'),
@@ -46,6 +70,7 @@ class SVTPlayIE(InfoExtractor):
self._sort_formats(formats)
duration = video_info.get('materialLength')
+ age_limit = 18 if video_info.get('inappropriateForChildren') else 0
return {
'id': video_id,
@@ -53,4 +78,5 @@ class SVTPlayIE(InfoExtractor):
'formats': formats,
'thumbnail': thumbnail,
'duration': duration,
+ 'age_limit': age_limit,
}
generated by cgit v1.2.3 (git 2.26.2) at 2025-04-09 12:46:05 +0000