summaryrefslogtreecommitdiffhomepage
diff options
context:
space:
mode:
authorSergey M․ <[email protected]>2014-07-16 19:13:35 +0700
committerSergey M․ <[email protected]>2014-07-16 19:13:35 +0700
commit1aa42fedee7df58ccd4e39b04a2a0438c5630f03 (patch)
tree5a8a52961f19d2989c6730a56e2bde95ccd35825
parentee90ddab94dd694f3d952954e4211e601c478d1e (diff)
parent172240c0a40f44d2aa384c512cc65c7e4c9e3660 (diff)
downloadyoutube-dl-1aa42fedee7df58ccd4e39b04a2a0438c5630f03.tar.gz
youtube-dl-1aa42fedee7df58ccd4e39b04a2a0438c5630f03.zip
Merge branch 'MLB' of https://github.com/chaochichen/youtube-dl into chaochichen-MLB
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/mlb.py74
2 files changed, 75 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index e49ac3e52..14133c315 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -170,6 +170,7 @@ from .metacafe import MetacafeIE
from .metacritic import MetacriticIE
from .mit import TechTVMITIE, MITIE, OCWMITIE
from .mixcloud import MixcloudIE
+from .mlb import MlbIE
from .mpora import MporaIE
from .mofosex import MofosexIE
from .mooshare import MooshareIE
diff --git a/youtube_dl/extractor/mlb.py b/youtube_dl/extractor/mlb.py
new file mode 100644
index 000000000..61ba58843
--- /dev/null
+++ b/youtube_dl/extractor/mlb.py
@@ -0,0 +1,74 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class MlbIE(InfoExtractor):
+ _VALID_URL = r'http?://m\.mlb\.com/video/topic/[0-9]+/v(?P<id>n?\d+)/.*$'
+ _TEST = {
+ 'url': 'http://m.mlb.com/video/topic/81536970/v34496663/mianym-stanton-practices-for-the-home-run-derby',
+ 'md5': u'd9c022c10d21f849f49c05ae12a8a7e9',
+ 'info_dict': {
+ 'id': '34496663',
+ 'ext': 'mp4',
+ 'format': 'mp4',
+ 'description': "7/11/14: Giancarlo Stanton practices for the Home Run Derby prior to the game against the Mets",
+ 'title': "Stanton prepares for Derby",
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
+ webpage = self._download_webpage(url, video_id)
+
+ title = self._og_search_title(webpage, default=video_id)
+ description = self._html_search_regex(r'<meta name="description" (?:content|value)="(.*?)"/>', webpage, 'description', fatal=False)
+ thumbnail = self._html_search_regex(r'<meta itemprop="image" (?:content|value)="(.*?)" />', webpage, 'image', fatal=False)
+
+ # use the video_id to find the Media detail XML
+ id_len = len(video_id)
+ _mediadetail_url = 'http://m.mlb.com/gen/multimedia/detail/'+video_id[id_len-3]+'/'+video_id[id_len-2]+'/'+video_id[id_len-1]+'/'+video_id+'.xml'
+
+ mediadetails = self._download_xml(_mediadetail_url, video_id, "Downloading media detail...")
+ has1500K = 0
+ has1200K = 0
+ has600K = 0
+ # loop through the list of url's and only get the highest quality MP4 content
+ for element in mediadetails.findall('url'):
+ scenario = element.attrib['playback_scenario']
+ if scenario.startswith(u'FLASH'):
+ if scenario.startswith(u'FLASH_1800K'):
+ video_url = element.text
+ # 1800K is the current highest quality video on MLB.com
+ break
+ else:
+ if scenario.startswith(u'FLASH_1500K'):
+ video_url = element.text
+ has1500K = 1
+ else:
+ if (scenario.startswith(u'FLASH_1200K') and not has1500K):
+ video_url = element.text
+ has1200K = 1
+ else:
+ if (scenario.startswith(u'FLASH_600K') and not has1200K):
+ video_url = element.text
+ has600K = 1
+ else:
+ if (scenario.startswith(u'FLASH_300K') and not has600K):
+ video_url = element.text
+
+ return {
+ 'id': video_id,
+ 'url': video_url,
+ 'extractor': 'mlb',
+ 'webpage_url': url,
+ 'title': title,
+ 'ext': 'mp4',
+ 'format': 'mp4',
+ 'description': description,
+ 'thumbnail': thumbnail,
+ }