aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/common.py11
-rw-r--r--youtube_dl/extractor/elpais.py6
-rw-r--r--youtube_dl/extractor/netzkino.py86
-rw-r--r--youtube_dl/extractor/wdr.py31
-rw-r--r--youtube_dl/extractor/youtube.py6
6 files changed, 129 insertions, 12 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 8dacc2c54..5da7568ca 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -274,6 +274,7 @@ from .nbc import (
)
from .ndr import NDRIE
from .ndtv import NDTVIE
+from .netzkino import NetzkinoIE
from .nerdcubed import NerdCubedFeedIE
from .newgrounds import NewgroundsIE
from .newstube import NewstubeIE
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index d703893dc..b4cd59e43 100644
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -147,6 +147,17 @@ class InfoExtractor(object):
like_count: Number of positive ratings of the video
dislike_count: Number of negative ratings of the video
comment_count: Number of comments on the video
+ comments: A list of comments, each with one or more of the following
+ properties (all but one of text or html optional):
+ * "author" - human-readable name of the comment author
+ * "author_id" - user ID of the comment author
+ * "id" - Comment ID
+ * "html" - Comment as HTML
+ * "text" - Plain text of the comment
+ * "timestamp" - UNIX timestamp of comment
+ * "parent" - ID of the comment this one is replying to.
+ Set to "root" to indicate that this is a
+ comment to the original video.
age_limit: Age restriction for the video, as an integer (years)
webpage_url: The url to the video webpage, if given to youtube-dl it
should allow to get the same result again. (It will be set
diff --git a/youtube_dl/extractor/elpais.py b/youtube_dl/extractor/elpais.py
index 4277202a2..00a69e631 100644
--- a/youtube_dl/extractor/elpais.py
+++ b/youtube_dl/extractor/elpais.py
@@ -1,8 +1,6 @@
# coding: utf-8
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
from ..utils import unified_strdate
@@ -24,9 +22,7 @@ class ElPaisIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
prefix = self._html_search_regex(
diff --git a/youtube_dl/extractor/netzkino.py b/youtube_dl/extractor/netzkino.py
new file mode 100644
index 000000000..93567d1e3
--- /dev/null
+++ b/youtube_dl/extractor/netzkino.py
@@ -0,0 +1,86 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ clean_html,
+ int_or_none,
+ js_to_json,
+ parse_iso8601,
+)
+
+
+class NetzkinoIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?netzkino\.de/\#!/(?P<category>[^/]+)/(?P<id>[^/]+)'
+
+ _TEST = {
+ 'url': 'http://www.netzkino.de/#!/scifikino/rakete-zum-mond',
+ 'md5': '92a3f8b76f8d7220acce5377ea5d4873',
+ 'info_dict': {
+ 'id': 'rakete-zum-mond',
+ 'ext': 'mp4',
+ 'title': 'Rakete zum Mond (Endstation Mond, Destination Moon)',
+ 'comments': 'mincount:3',
+ 'description': 'md5:1eddeacc7e62d5a25a2d1a7290c64a28',
+ 'upload_date': '20120813',
+ 'thumbnail': 're:https?://.*\.jpg$',
+ 'timestamp': 1344858571,
+ 'age_limit': 12,
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ category_id = mobj.group('category')
+ video_id = mobj.group('id')
+
+ api_url = 'http://api.netzkino.de.simplecache.net/capi-2.0a/categories/%s.json?d=www' % category_id
+ api_info = self._download_json(api_url, video_id)
+ info = next(
+ p for p in api_info['posts'] if p['slug'] == video_id)
+ custom_fields = info['custom_fields']
+
+ production_js = self._download_webpage(
+ 'http://www.netzkino.de/beta/dist/production.min.js', video_id,
+ note='Downloading player code')
+ avo_js = self._search_regex(
+ r'window\.avoCore\s*=.*?urlTemplate:\s*(\{.*?"\})',
+ production_js, 'URL templates')
+ templates = self._parse_json(
+ avo_js, video_id, transform_source=js_to_json)
+
+ suffix = {
+ 'hds': '.mp4/manifest.f4m',
+ 'hls': '.mp4/master.m3u8',
+ 'pmd': '.mp4',
+ }
+ film_fn = custom_fields['Streaming'][0]
+ formats = [{
+ 'format_id': key,
+ 'ext': 'mp4',
+ 'url': tpl.replace('{}', film_fn) + suffix[key],
+ } for key, tpl in templates.items()]
+ self._sort_formats(formats)
+
+ comments = [{
+ 'timestamp': parse_iso8601(c.get('date'), delimiter=' '),
+ 'id': c['id'],
+ 'author': c['name'],
+ 'html': c['content'],
+ 'parent': 'root' if c.get('parent', 0) == 0 else c['parent'],
+ } for c in info.get('comments', [])]
+
+ return {
+ 'id': video_id,
+ 'formats': formats,
+ 'comments': comments,
+ 'title': info['title'],
+ 'age_limit': int_or_none(custom_fields.get('FSK')[0]),
+ 'timestamp': parse_iso8601(info.get('date'), delimiter=' '),
+ 'description': clean_html(info.get('content')),
+ 'thumbnail': info.get('thumbnail'),
+ 'playlist_title': api_info.get('title'),
+ 'playlist_id': category_id,
+ }
diff --git a/youtube_dl/extractor/wdr.py b/youtube_dl/extractor/wdr.py
index 8e25ecf28..45466e31b 100644
--- a/youtube_dl/extractor/wdr.py
+++ b/youtube_dl/extractor/wdr.py
@@ -1,6 +1,7 @@
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
+import itertools
import re
from .common import InfoExtractor
@@ -67,6 +68,10 @@ class WDRIE(InfoExtractor):
'upload_date': '20140717',
},
},
+ {
+ 'url': 'http://www1.wdr.de/mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100.html',
+ 'playlist_mincount': 146,
+ }
]
def _real_extract(self, url):
@@ -81,6 +86,27 @@ class WDRIE(InfoExtractor):
self.url_result(page_url + href, 'WDR')
for href in re.findall(r'<a href="/?(.+?%s\.html)" rel="nofollow"' % self._PLAYER_REGEX, webpage)
]
+
+ if entries: # Playlist page
+ return self.playlist_result(entries, page_id)
+
+ # Overview page
+ entries = []
+ for page_num in itertools.count(2):
+ hrefs = re.findall(
+ r'<li class="mediathekvideo"\s*>\s*<img[^>]*>\s*<a href="(/mediathek/video/[^"]+)"',
+ webpage)
+ entries.extend(
+ self.url_result(page_url + href, 'WDR')
+ for href in hrefs)
+ next_url_m = re.search(
+ r'<li class="nextToLast">\s*<a href="([^"]+)"', webpage)
+ if not next_url_m:
+ break
+ next_url = page_url + next_url_m.group(1)
+ webpage = self._download_webpage(
+ next_url, page_id,
+ note='Downloading playlist page %d' % page_num)
return self.playlist_result(entries, page_id)
flashvars = compat_parse_qs(
@@ -172,8 +198,7 @@ class WDRMausIE(InfoExtractor):
}]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
param_code = self._html_search_regex(
@@ -224,5 +249,3 @@ class WDRMausIE(InfoExtractor):
'thumbnail': thumbnail,
'upload_date': upload_date,
}
-
-# TODO test _1
diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index e71956071..bc18276d6 100644
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -264,9 +264,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
'266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'h264'},
# Dash mp4 audio
- '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'vcodec': 'none', 'abr': 48, 'preference': -50},
- '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'vcodec': 'none', 'abr': 128, 'preference': -50},
- '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'vcodec': 'none', 'abr': 256, 'preference': -50},
+ '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 48, 'preference': -50},
+ '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 128, 'preference': -50},
+ '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 256, 'preference': -50},
# Dash webm
'167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
generated by cgit v1.2.3 (git 2.26.2) at 2025-04-15 15:05:30 +0000