etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 03:03:01 +00:00
Code Issues Projects Releases Wiki Activity

[mit] Modernize

Browse source
This commit is contained in:
Philipp Hagemeister 2014-02-26 00:06:31 +01:00
parent f3ac523794
commit 5b2478e2ba
1 changed files with 37 additions and 30 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

57
youtube_dl/extractor/mit.py
View file

@ -1,24 +1,28 @@
from __future__ import unicode_literals
import re import re
import json import json
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
compat_urlparse,
clean_html, clean_html,
get_element_by_id, get_element_by_id,
) )
class TechTVMITIE(InfoExtractor): class TechTVMITIE(InfoExtractor):
IE_NAME = u'techtv.mit.edu' IE_NAME = 'techtv.mit.edu'
_VALID_URL = r'https?://techtv\.mit\.edu/(videos|embeds)/(?P<id>\d+)' _VALID_URL = r'https?://techtv\.mit\.edu/(videos|embeds)/(?P<id>\d+)'
_TEST = { _TEST = {
u'url': u'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set', 'url': 'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set',
u'file': u'25418.mp4', 'md5': '1f8cb3e170d41fd74add04d3c9330e5f',
u'md5': u'1f8cb3e170d41fd74add04d3c9330e5f', 'info_dict': {
u'info_dict': { 'id': '25418',
u'title': u'MIT DNA Learning Center Set', 'ext': 'mp4',
u'description': u'md5:82313335e8a8a3f243351ba55bc1b474', 'title': 'MIT DNA Learning Center Set',
'description': 'md5:82313335e8a8a3f243351ba55bc1b474',
}, },
} }
@ -27,12 +31,12 @@ def _real_extract(self, url):
video_id = mobj.group('id') video_id = mobj.group('id')
raw_page = self._download_webpage( raw_page = self._download_webpage(
'http://techtv.mit.edu/videos/%s' % video_id, video_id) 'http://techtv.mit.edu/videos/%s' % video_id, video_id)
clean_page = re.compile(u'<!--.*?-->', re.S).sub(u'', raw_page) clean_page = re.compile(r'<!--.*?-->', re.S).sub('', raw_page)
base_url = self._search_regex(r'ipadUrl: \'(.+?cloudfront.net/)', base_url = self._search_regex(
raw_page, u'base url') r'ipadUrl: \'(.+?cloudfront.net/)', raw_page, 'base url')
formats_json = self._search_regex(r'bitrates: (\[.+?\])', raw_page, formats_json = self._search_regex(
u'video formats') r'bitrates: (\[.+?\])', raw_page, 'video formats')
formats_mit = json.loads(formats_json) formats_mit = json.loads(formats_json)
formats = [ formats = [
{ {
@ -48,10 +52,12 @@ def _real_extract(self, url):
title = get_element_by_id('edit-title', clean_page) title = get_element_by_id('edit-title', clean_page)
description = clean_html(get_element_by_id('edit-description', clean_page)) description = clean_html(get_element_by_id('edit-description', clean_page))
thumbnail = self._search_regex(r'playlist:.*?url: \'(.+?)\'', thumbnail = self._search_regex(
raw_page, u'thumbnail', flags=re.DOTALL) r'playlist:.*?url: \'(.+?)\'',
raw_page, 'thumbnail', flags=re.DOTALL)
return {'id': video_id, return {
'id': video_id,
'title': title, 'title': title,
'formats': formats, 'formats': formats,
'description': description, 'description': description,
@ -60,16 +66,18 @@ def _real_extract(self, url):
class MITIE(TechTVMITIE): class MITIE(TechTVMITIE):
IE_NAME = u'video.mit.edu' IE_NAME = 'video.mit.edu'
_VALID_URL = r'https?://video\.mit\.edu/watch/(?P<title>[^/]+)' _VALID_URL = r'https?://video\.mit\.edu/watch/(?P<title>[^/]+)'
_TEST = { _TEST = {
u'url': u'http://video.mit.edu/watch/the-government-is-profiling-you-13222/', 'url': 'http://video.mit.edu/watch/the-government-is-profiling-you-13222/',
u'file': u'21783.mp4', 'file': '.mp4',
u'md5': u'7db01d5ccc1895fc5010e9c9e13648da', 'md5': '7db01d5ccc1895fc5010e9c9e13648da',
u'info_dict': { 'info_dict': {
u'title': u'The Government is Profiling You', 'id': '21783',
u'description': u'md5:ad5795fe1e1623b73620dbfd47df9afd', 'ext': 'mp4',
'title': 'The Government is Profiling You',
'description': 'md5:ad5795fe1e1623b73620dbfd47df9afd',
}, },
} }
@ -77,7 +85,6 @@ def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
page_title = mobj.group('title') page_title = mobj.group('title')
webpage = self._download_webpage(url, page_title) webpage = self._download_webpage(url, page_title)
self.to_screen('%s: Extracting %s url' % (page_title, TechTVMITIE.IE_NAME)) embed_url = self._search_regex(
embed_url = self._search_regex(r'<iframe .*?src="(.+?)"', webpage, r'<iframe .*?src="(.+?)"', webpage, 'embed url')
u'embed url')
return self.url_result(embed_url, ie='TechTVMIT') return self.url_result(embed_url, ie='TechTVMIT')