aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorRemita Amine <remitamine@gmail.com>2019-07-11 23:37:34 +0100
committerRemita Amine <remitamine@gmail.com>2019-07-11 23:37:34 +0100
commit16d3672ad73802043a9cccd1505909949e2ce71f (patch)
treeb07c2a879d14fd510ecb12d2d66674aea610b528
parent0dd58a523fffd06c126c006722850bab36bd3aa2 (diff)
[espn] fix fivethirtyeight.com extraction
-rw-r--r--youtube_dl/extractor/abcnews.py9
-rw-r--r--youtube_dl/extractor/espn.py16
2 files changed, 12 insertions, 13 deletions
diff --git a/youtube_dl/extractor/abcnews.py b/youtube_dl/extractor/abcnews.py
index cd29aca77..8b407bf9c 100644
--- a/youtube_dl/extractor/abcnews.py
+++ b/youtube_dl/extractor/abcnews.py
@@ -15,10 +15,13 @@ class AbcNewsVideoIE(AMPIE):
IE_NAME = 'abcnews:video'
_VALID_URL = r'''(?x)
https?://
- abcnews\.go\.com/
(?:
- [^/]+/video/(?P<display_id>[0-9a-z-]+)-|
- video/embed\?.*?\bid=
+ abcnews\.go\.com/
+ (?:
+ [^/]+/video/(?P<display_id>[0-9a-z-]+)-|
+ video/embed\?.*?\bid=
+ )|
+ fivethirtyeight\.abcnews\.go\.com/video/embed/\d+/
)
(?P<id>\d+)
'''
diff --git a/youtube_dl/extractor/espn.py b/youtube_dl/extractor/espn.py
index 8cc9bd165..6cf05e6da 100644
--- a/youtube_dl/extractor/espn.py
+++ b/youtube_dl/extractor/espn.py
@@ -216,17 +216,14 @@ class FiveThirtyEightIE(InfoExtractor):
_TEST = {
'url': 'http://fivethirtyeight.com/features/how-the-6-8-raiders-can-still-make-the-playoffs/',
'info_dict': {
- 'id': '21846851',
- 'ext': 'mp4',
+ 'id': '56032156',
+ 'ext': 'flv',
'title': 'FiveThirtyEight: The Raiders can still make the playoffs',
'description': 'Neil Paine breaks down the simplest scenario that will put the Raiders into the playoffs at 8-8.',
- 'timestamp': 1513960621,
- 'upload_date': '20171222',
},
'params': {
'skip_download': True,
},
- 'expected_warnings': ['Unable to download f4m manifest'],
}
def _real_extract(self, url):
@@ -234,9 +231,8 @@ class FiveThirtyEightIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
- video_id = self._search_regex(
- r'data-video-id=["\'](?P<id>\d+)',
- webpage, 'video id', group='id')
+ embed_url = self._search_regex(
+ r'<iframe[^>]+src=["\'](https?://fivethirtyeight\.abcnews\.go\.com/video/embed/\d+/\d+)',
+ webpage, 'embed url')
- return self.url_result(
- 'http://espn.go.com/video/clip?id=%s' % video_id, ESPNIE.ie_key())
+ return self.url_result(embed_url, 'AbcNewsVideo')