aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorPhilipp Hagemeister <phihag@phihag.de>2013-06-23 21:55:53 +0200
committerPhilipp Hagemeister <phihag@phihag.de>2013-06-23 21:55:53 +0200
commit9fd5ce0cbe473b7f70246b09e7f480507d8d2acf (patch)
tree2befb31f3637f86d996ad405c99b14303e0f0872
parent1736dec629bd3da25bea21145794adfa7a835ea3 (diff)
Move TED IE into its own file
-rwxr-xr-xyoutube_dl/InfoExtractors.py75
-rw-r--r--youtube_dl/extractor/ted.py79
2 files changed, 80 insertions, 74 deletions
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 9d885d238..fd4409952 100755
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -40,6 +40,7 @@ from .extractor.statigram import StatigramIE
from .extractor.photobucket import PhotobucketIE
from .extractor.soundcloud import SoundcloudIE, SoundcloudSetIE
from .extractor.stanfordoc import StanfordOpenClassroomIE
+from .extractor.ted import TEDIE
from .extractor.vimeo import VimeoIE
from .extractor.xvideos import XVideosIE
from .extractor.yahoo import YahooIE, YahooSearchIE
@@ -868,80 +869,6 @@ class KeekIE(InfoExtractor):
}
return [info]
-class TEDIE(InfoExtractor):
- _VALID_URL=r'''http://www\.ted\.com/
- (
- ((?P<type_playlist>playlists)/(?P<playlist_id>\d+)) # We have a playlist
- |
- ((?P<type_talk>talks)) # We have a simple talk
- )
- (/lang/(.*?))? # The url may contain the language
- /(?P<name>\w+) # Here goes the name and then ".html"
- '''
-
- @classmethod
- def suitable(cls, url):
- """Receives a URL and returns True if suitable for this IE."""
- return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
-
- def _real_extract(self, url):
- m=re.match(self._VALID_URL, url, re.VERBOSE)
- if m.group('type_talk'):
- return [self._talk_info(url)]
- else :
- playlist_id=m.group('playlist_id')
- name=m.group('name')
- self.to_screen(u'Getting info of playlist %s: "%s"' % (playlist_id,name))
- return [self._playlist_videos_info(url,name,playlist_id)]
-
- def _playlist_videos_info(self,url,name,playlist_id=0):
- '''Returns the videos of the playlist'''
- video_RE=r'''
- <li\ id="talk_(\d+)"([.\s]*?)data-id="(?P<video_id>\d+)"
- ([.\s]*?)data-playlist_item_id="(\d+)"
- ([.\s]*?)data-mediaslug="(?P<mediaSlug>.+?)"
- '''
- video_name_RE=r'<p\ class="talk-title"><a href="(?P<talk_url>/talks/(.+).html)">(?P<fullname>.+?)</a></p>'
- webpage=self._download_webpage(url, playlist_id, 'Downloading playlist webpage')
- m_videos=re.finditer(video_RE,webpage,re.VERBOSE)
- m_names=re.finditer(video_name_RE,webpage)
-
- playlist_title = self._html_search_regex(r'div class="headline">\s*?<h1>\s*?<span>(.*?)</span>',
- webpage, 'playlist title')
-
- playlist_entries = []
- for m_video, m_name in zip(m_videos,m_names):
- video_id=m_video.group('video_id')
- talk_url='http://www.ted.com%s' % m_name.group('talk_url')
- playlist_entries.append(self.url_result(talk_url, 'TED'))
- return self.playlist_result(playlist_entries, playlist_id = playlist_id, playlist_title = playlist_title)
-
- def _talk_info(self, url, video_id=0):
- """Return the video for the talk in the url"""
- m = re.match(self._VALID_URL, url,re.VERBOSE)
- video_name = m.group('name')
- webpage = self._download_webpage(url, video_id, 'Downloading \"%s\" page' % video_name)
- self.report_extraction(video_name)
- # If the url includes the language we get the title translated
- title = self._html_search_regex(r'<span id="altHeadline" >(?P<title>.*)</span>',
- webpage, 'title')
- json_data = self._search_regex(r'<script.*?>var talkDetails = ({.*?})</script>',
- webpage, 'json data')
- info = json.loads(json_data)
- desc = self._html_search_regex(r'<div class="talk-intro">.*?<p.*?>(.*?)</p>',
- webpage, 'description', flags = re.DOTALL)
-
- thumbnail = self._search_regex(r'</span>[\s.]*</div>[\s.]*<img src="(.*?)"',
- webpage, 'thumbnail')
- info = {
- 'id': info['id'],
- 'url': info['htmlStreams'][-1]['file'],
- 'ext': 'mp4',
- 'title': title,
- 'thumbnail': thumbnail,
- 'description': desc,
- }
- return info
class MySpassIE(InfoExtractor):
_VALID_URL = r'http://www.myspass.de/.*'
diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py
new file mode 100644
index 000000000..ccad1c7c2
--- /dev/null
+++ b/youtube_dl/extractor/ted.py
@@ -0,0 +1,79 @@
+import json
+import re
+
+from .common import InfoExtractor
+
+
+class TEDIE(InfoExtractor):
+ _VALID_URL=r'''http://www\.ted\.com/
+ (
+ ((?P<type_playlist>playlists)/(?P<playlist_id>\d+)) # We have a playlist
+ |
+ ((?P<type_talk>talks)) # We have a simple talk
+ )
+ (/lang/(.*?))? # The url may contain the language
+ /(?P<name>\w+) # Here goes the name and then ".html"
+ '''
+
+ @classmethod
+ def suitable(cls, url):
+ """Receives a URL and returns True if suitable for this IE."""
+ return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
+
+ def _real_extract(self, url):
+ m=re.match(self._VALID_URL, url, re.VERBOSE)
+ if m.group('type_talk'):
+ return [self._talk_info(url)]
+ else :
+ playlist_id=m.group('playlist_id')
+ name=m.group('name')
+ self.to_screen(u'Getting info of playlist %s: "%s"' % (playlist_id,name))
+ return [self._playlist_videos_info(url,name,playlist_id)]
+
+ def _playlist_videos_info(self,url,name,playlist_id=0):
+ '''Returns the videos of the playlist'''
+ video_RE=r'''
+ <li\ id="talk_(\d+)"([.\s]*?)data-id="(?P<video_id>\d+)"
+ ([.\s]*?)data-playlist_item_id="(\d+)"
+ ([.\s]*?)data-mediaslug="(?P<mediaSlug>.+?)"
+ '''
+ video_name_RE=r'<p\ class="talk-title"><a href="(?P<talk_url>/talks/(.+).html)">(?P<fullname>.+?)</a></p>'
+ webpage=self._download_webpage(url, playlist_id, 'Downloading playlist webpage')
+ m_videos=re.finditer(video_RE,webpage,re.VERBOSE)
+ m_names=re.finditer(video_name_RE,webpage)
+
+ playlist_title = self._html_search_regex(r'div class="headline">\s*?<h1>\s*?<span>(.*?)</span>',
+ webpage, 'playlist title')
+
+ playlist_entries = []
+ for m_video, m_name in zip(m_videos,m_names):
+ talk_url='http://www.ted.com%s' % m_name.group('talk_url')
+ playlist_entries.append(self.url_result(talk_url, 'TED'))
+ return self.playlist_result(playlist_entries, playlist_id = playlist_id, playlist_title = playlist_title)
+
+ def _talk_info(self, url, video_id=0):
+ """Return the video for the talk in the url"""
+ m = re.match(self._VALID_URL, url,re.VERBOSE)
+ video_name = m.group('name')
+ webpage = self._download_webpage(url, video_id, 'Downloading \"%s\" page' % video_name)
+ self.report_extraction(video_name)
+ # If the url includes the language we get the title translated
+ title = self._html_search_regex(r'<span id="altHeadline" >(?P<title>.*)</span>',
+ webpage, 'title')
+ json_data = self._search_regex(r'<script.*?>var talkDetails = ({.*?})</script>',
+ webpage, 'json data')
+ info = json.loads(json_data)
+ desc = self._html_search_regex(r'<div class="talk-intro">.*?<p.*?>(.*?)</p>',
+ webpage, 'description', flags = re.DOTALL)
+
+ thumbnail = self._search_regex(r'</span>[\s.]*</div>[\s.]*<img src="(.*?)"',
+ webpage, 'thumbnail')
+ info = {
+ 'id': info['id'],
+ 'url': info['htmlStreams'][-1]['file'],
+ 'ext': 'mp4',
+ 'title': title,
+ 'thumbnail': thumbnail,
+ 'description': desc,
+ }
+ return info