aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
authorYen Chi Hsuan <yan12125@gmail.com>2016-07-06 23:37:54 +0800
committerYen Chi Hsuan <yan12125@gmail.com>2016-07-06 23:37:54 +0800
commitad213a1d74d41e798ed065d4285ebc25135e1138 (patch)
tree76fab047d9ffc0caf3b68f077d7fad5e559ce250 /youtube_dl/extractor
parent43f1e4e41e1900786e7d5186d2844e9b307bc05e (diff)
[francetv] Recognize more Dailymotion embedded videos
Closes #9955
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/dailymotion.py7
-rw-r--r--youtube_dl/extractor/francetv.py28
-rw-r--r--youtube_dl/extractor/generic.py12
3 files changed, 39 insertions, 8 deletions
diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py
index 15bfc59b2..1f92823b7 100644
--- a/youtube_dl/extractor/dailymotion.py
+++ b/youtube_dl/extractor/dailymotion.py
@@ -112,6 +112,13 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
}
]
+ @staticmethod
+ def _extract_urls(webpage):
+ # Look for embedded Dailymotion player
+ matches = re.findall(
+ r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
+ return list(map(lambda m: unescapeHTML(m[1]), matches))
+
def _real_extract(self, url):
video_id = self._match_id(url)
diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py
index ad94e31f3..7653975e3 100644
--- a/youtube_dl/extractor/francetv.py
+++ b/youtube_dl/extractor/francetv.py
@@ -14,7 +14,10 @@ from ..utils import (
parse_duration,
determine_ext,
)
-from .dailymotion import DailymotionCloudIE
+from .dailymotion import (
+ DailymotionIE,
+ DailymotionCloudIE,
+)
class FranceTVBaseInfoExtractor(InfoExtractor):
@@ -188,6 +191,21 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
'params': {
'skip_download': True,
},
+ }, {
+ # Dailymotion embed
+ 'url': 'http://www.francetvinfo.fr/politique/notre-dame-des-landes/video-sur-france-inter-cecile-duflot-denonce-le-regard-meprisant-de-patrick-cohen_1520091.html',
+ 'md5': 'ee7f1828f25a648addc90cb2687b1f12',
+ 'info_dict': {
+ 'id': 'x4iiko0',
+ 'ext': 'mp4',
+ 'title': 'NDDL, référendum, Brexit : Cécile Duflot répond à Patrick Cohen',
+ 'description': 'Au lendemain de la victoire du "oui" au référendum sur l\'aéroport de Notre-Dame-des-Landes, l\'ancienne ministre écologiste est l\'invitée de Patrick Cohen. Plus d\'info : https://www.franceinter.fr/emissions/le-7-9/le-7-9-27-juin-2016',
+ 'timestamp': 1467011958,
+ 'upload_date': '20160627',
+ 'uploader': 'France Inter',
+ 'uploader_id': 'x2q2ez',
+ },
+ 'add_ie': ['Dailymotion'],
}]
def _real_extract(self, url):
@@ -197,7 +215,13 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
if dmcloud_url:
- return self.url_result(dmcloud_url, 'DailymotionCloud')
+ return self.url_result(dmcloud_url, DailymotionCloudIE.ie_key())
+
+ dailymotion_urls = DailymotionIE._extract_urls(webpage)
+ if dailymotion_urls:
+ return self.playlist_result([
+ self.url_result(dailymotion_url, DailymotionIE.ie_key())
+ for dailymotion_url in dailymotion_urls])
video_id, catalogue = self._search_regex(
(r'id-video=([^@]+@[^"]+)',
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 764697bd2..31527d1c6 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -49,7 +49,10 @@ from .pornhub import PornHubIE
from .xhamster import XHamsterEmbedIE
from .tnaflix import TNAFlixNetworkEmbedIE
from .vimeo import VimeoIE
-from .dailymotion import DailymotionCloudIE
+from .dailymotion import (
+ DailymotionIE,
+ DailymotionCloudIE,
+)
from .onionstudios import OnionStudiosIE
from .viewlift import ViewLiftEmbedIE
from .screenwavemedia import ScreenwaveMediaIE
@@ -1673,12 +1676,9 @@ class GenericIE(InfoExtractor):
if matches:
return _playlist_from_matches(matches, lambda m: m[-1])
- # Look for embedded Dailymotion player
- matches = re.findall(
- r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
+ matches = DailymotionIE._extract_urls(webpage)
if matches:
- return _playlist_from_matches(
- matches, lambda m: unescapeHTML(m[1]))
+ return _playlist_from_matches(matches)
# Look for embedded Dailymotion playlist player (#3822)
m = re.search(