[dailymotion] Added support for subtitles + new InfoExtractor for

generic subtitle download.

The idea is that all subtitle downloaders must descend from SubtitlesIE
and implement only three basic methods to achieve the complete subtitle
download functionality. This will allow to reduce the code in YoutubeIE
once it is rewritten.
This commit is contained in:
Ismael Mejia 2013-08-07 18:59:11 +02:00
parent 5898e28272
commit 953e32b2c1
4 changed files with 242 additions and 11 deletions

View File

@ -0,0 +1,96 @@
#!/usr/bin/env python
import sys
import unittest
import json
import io
import hashlib
# Allow direct execution
import os
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.extractor import DailymotionIE
from youtube_dl.utils import *
from helper import FakeYDL
md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
TEST_URL = 'http://www.dailymotion.com/video/xczg00'
class TestDailymotionSubtitles(unittest.TestCase):
def setUp(self):
DL = FakeYDL()
DL.params['allsubtitles'] = False
DL.params['writesubtitles'] = False
DL.params['subtitlesformat'] = 'srt'
DL.params['listsubtitles'] = False
def test_no_subtitles(self):
DL = FakeYDL()
DL.params['writesubtitles'] = False
IE = DailymotionIE(DL)
info_dict = IE.extract(TEST_URL)
subtitles = info_dict[0]['subtitles']
self.assertEqual(subtitles, None)
def test_subtitles(self):
DL = FakeYDL()
DL.params['writesubtitles'] = True
IE = DailymotionIE(DL)
info_dict = IE.extract(TEST_URL)
sub = info_dict[0]['subtitles']['en']
self.assertEqual(md5(sub), '976553874490cba125086bbfea3ff76f')
def test_subtitles_fr(self):
DL = FakeYDL()
DL.params['writesubtitles'] = True
DL.params['subtitleslang'] = 'fr'
IE = DailymotionIE(DL)
info_dict = IE.extract(TEST_URL)
sub = info_dict[0]['subtitles']['fr']
self.assertEqual(md5(sub), '594564ec7d588942e384e920e5341792')
def test_onlysubtitles(self):
DL = FakeYDL()
DL.params['writesubtitles'] = True
DL.params['onlysubtitles'] = True
IE = DailymotionIE(DL)
info_dict = IE.extract(TEST_URL)
sub = info_dict[0]['subtitles']['en']
self.assertEqual(md5(sub), '976553874490cba125086bbfea3ff76f')
def test_allsubtitles(self):
DL = FakeYDL()
DL.params['allsubtitles'] = True
IE = DailymotionIE(DL)
info_dict = IE.extract(TEST_URL)
subtitles = info_dict[0]['subtitles']
self.assertEqual(len(subtitles.keys()), 5)
# def test_subtitles_sbv_format(self):
# DL = FakeYDL()
# DL.params['writesubtitles'] = True
# DL.params['subtitlesformat'] = 'sbv'
# IE = DailymotionIE(DL)
# info_dict = IE.extract(TEST_URL)
# sub = info_dict[0]['subtitles'][0]
# self.assertEqual(md5(sub), '13aeaa0c245a8bed9a451cb643e3ad8b')
# def test_subtitles_vtt_format(self):
# DL = FakeYDL()
# DL.params['writesubtitles'] = True
# DL.params['subtitlesformat'] = 'vtt'
# IE = DailymotionIE(DL)
# info_dict = IE.extract(TEST_URL)
# sub = info_dict[0]['subtitles'][0]
# self.assertEqual(md5(sub), '356cdc577fde0c6783b9b822e7206ff7')
def test_list_subtitles(self):
DL = FakeYDL()
DL.params['listsubtitles'] = True
IE = DailymotionIE(DL)
info_dict = IE.extract(TEST_URL)
self.assertEqual(info_dict, None)
def test_automatic_captions(self):
DL = FakeYDL()
DL.params['writeautomaticsub'] = True
DL.params['subtitleslang'] = 'en'
IE = DailymotionIE(DL)
info_dict = IE.extract(TEST_URL)
sub = info_dict[0]['subtitles']
self.assertTrue(len(sub) == 0)
if __name__ == '__main__':
unittest.main()

View File

@ -187,22 +187,22 @@ def _find_term_columns():
action='store_true', dest='listformats', help='list all available formats (currently youtube only)') action='store_true', dest='listformats', help='list all available formats (currently youtube only)')
video_format.add_option('--write-sub', '--write-srt', video_format.add_option('--write-sub', '--write-srt',
action='store_true', dest='writesubtitles', action='store_true', dest='writesubtitles',
help='write subtitle file (currently youtube only)', default=False) help='write subtitle file', default=False)
video_format.add_option('--write-auto-sub', '--write-automatic-sub', video_format.add_option('--write-auto-sub', '--write-automatic-sub',
action='store_true', dest='writeautomaticsub', action='store_true', dest='writeautomaticsub',
help='write automatic subtitle file (currently youtube only)', default=False) help='write automatic subtitle file (youtube only)', default=False)
video_format.add_option('--only-sub', video_format.add_option('--only-sub',
action='store_true', dest='skip_download', action='store_true', dest='skip_download',
help='[deprecated] alias of --skip-download', default=False) help='[deprecated] alias of --skip-download', default=False)
video_format.add_option('--all-subs', video_format.add_option('--all-subs',
action='store_true', dest='allsubtitles', action='store_true', dest='allsubtitles',
help='downloads all the available subtitles of the video (currently youtube only)', default=False) help='downloads all the available subtitles of the video', default=False)
video_format.add_option('--list-subs', video_format.add_option('--list-subs',
action='store_true', dest='listsubtitles', action='store_true', dest='listsubtitles',
help='lists all available subtitles for the video (currently youtube only)', default=False) help='lists all available subtitles for the video', default=False)
video_format.add_option('--sub-format', video_format.add_option('--sub-format',
action='store', dest='subtitlesformat', metavar='FORMAT', action='store', dest='subtitlesformat', metavar='FORMAT',
help='subtitle format [srt/sbv/vtt] (default=srt) (currently youtube only)', default='srt') help='subtitle format (default=srt) ([sbv/vtt] youtube only)', default='srt')
video_format.add_option('--sub-lang', '--srt-lang', video_format.add_option('--sub-lang', '--srt-lang',
action='store', dest='subtitleslang', metavar='LANG', action='store', dest='subtitleslang', metavar='LANG',
help='language of the subtitles to download (optional) use IETF language tags like \'en\'') help='language of the subtitles to download (optional) use IETF language tags like \'en\'')

View File

@ -1,14 +1,49 @@
import re import re
import json import json
import itertools
import socket
from .common import InfoExtractor from .common import InfoExtractor
from .subtitles import SubtitlesIE
from ..utils import ( from ..utils import (
compat_http_client,
compat_urllib_error,
compat_urllib_request, compat_urllib_request,
compat_str,
get_element_by_attribute,
get_element_by_id,
ExtractorError, ExtractorError,
) )
class DailymotionIE(InfoExtractor):
class DailyMotionSubtitlesIE(SubtitlesIE):
def _get_available_subtitles(self, video_id):
request = compat_urllib_request.Request('https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id)
try:
sub_list = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.report_warning(u'unable to download video subtitles: %s' % compat_str(err))
return {}
info = json.loads(sub_list)
if (info['total'] > 0):
sub_lang_list = dict((l['language'], l['url']) for l in info['list'])
return sub_lang_list
self._downloader.report_warning(u'video doesn\'t have subtitles')
return {}
def _get_subtitle_url(self, sub_lang, sub_name, video_id, format):
sub_lang_list = self._get_available_subtitles(video_id)
return sub_lang_list[sub_lang]
def _request_automatic_caption(self, video_id, webpage):
self._downloader.report_warning(u'Automatic Captions not supported by dailymotion')
return {}
class DailymotionIE(DailyMotionSubtitlesIE): #,InfoExtractor):
"""Information Extractor for Dailymotion""" """Information Extractor for Dailymotion"""
_VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)' _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
@ -62,12 +97,31 @@ def _real_extract(self, url):
'stream_h264_ld_url']: 'stream_h264_ld_url']:
if info.get(key): # key in info and info[key]: if info.get(key): # key in info and info[key]:
max_quality = key max_quality = key
self.to_screen(u'Using %s' % key) self.to_screen(u'%s: Using %s' % (video_id, key))
break break
else: else:
raise ExtractorError(u'Unable to extract video URL') raise ExtractorError(u'Unable to extract video URL')
video_url = info[max_quality] video_url = info[max_quality]
# subtitles
video_subtitles = None
video_webpage = None
if self._downloader.params.get('writesubtitles', False) or self._downloader.params.get('allsubtitles', False):
video_subtitles = self._extract_subtitles(video_id)
elif self._downloader.params.get('writeautomaticsub', False):
video_subtitles = self._request_automatic_caption(video_id, video_webpage)
if self._downloader.params.get('listsubtitles', False):
self._list_available_subtitles(video_id)
return
if 'length_seconds' not in info:
self._downloader.report_warning(u'unable to extract video duration')
video_duration = ''
else:
video_duration = compat_urllib_parse.unquote_plus(video_info['length_seconds'][0])
return [{ return [{
'id': video_id, 'id': video_id,
'url': video_url, 'url': video_url,
@ -75,5 +129,6 @@ def _real_extract(self, url):
'upload_date': video_upload_date, 'upload_date': video_upload_date,
'title': self._og_search_title(webpage), 'title': self._og_search_title(webpage),
'ext': video_extension, 'ext': video_extension,
'subtitles': video_subtitles,
'thumbnail': info['thumbnail_url'] 'thumbnail': info['thumbnail_url']
}] }]

View File

@ -0,0 +1,80 @@
import socket
from .common import InfoExtractor
from ..utils import (
compat_http_client,
compat_urllib_error,
compat_urllib_request,
compat_str,
)
class SubtitlesIE(InfoExtractor):
def report_video_subtitles_available(self, video_id, sub_lang_list):
"""Report available subtitles."""
sub_lang = ",".join(list(sub_lang_list.keys()))
self.to_screen(u'%s: Available subtitles for video: %s' % (video_id, sub_lang))
def _list_available_subtitles(self, video_id):
sub_lang_list = self._get_available_subtitles(video_id)
self.report_video_subtitles_available(video_id, sub_lang_list)
def _extract_subtitles(self, video_id):
"""
Return a dictionary: {language: subtitles} or {} if the subtitles
couldn't be found
"""
sub_lang_list = self._get_available_subtitles(video_id)
sub_format = self._downloader.params.get('subtitlesformat')
if not sub_lang_list: #There was some error, it didn't get the available subtitles
return {}
if self._downloader.params.get('writesubtitles', False):
if self._downloader.params.get('subtitleslang', False):
sub_lang = self._downloader.params.get('subtitleslang')
elif 'en' in sub_lang_list:
sub_lang = 'en'
else:
sub_lang = list(sub_lang_list.keys())[0]
if not sub_lang in sub_lang_list:
self._downloader.report_warning(u'no closed captions found in the specified language "%s"' % sub_lang)
return {}
sub_lang_list = {sub_lang: sub_lang_list[sub_lang]}
subtitles = {}
for sub_lang in sub_lang_list:
subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format)
if subtitle:
subtitles[sub_lang] = subtitle
return subtitles
def _request_subtitle(self, sub_lang, sub_name, video_id, format):
""" Return the subtitle as a string or None if they are not found """
# return (u'Did not fetch video subtitles for %s' % sub_lang, None, None)
self.to_screen(u'%s: Downloading video subtitles for %s.%s' % (video_id, sub_lang, format))
url = self._get_subtitle_url(sub_lang, sub_name, video_id, format)
try:
sub = compat_urllib_request.urlopen(url).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.report_warning(u'unable to download video subtitles for %s: %s' % (sub_lang, compat_str(err)))
return
if not sub:
self._downloader.report_warning(u'Did not fetch video subtitles')
return
return sub
def _get_available_subtitles(self, video_id):
"""Get available subtitles. Redefine in subclasses."""
"""returns {(lang, url)} """
# return {}
pass
def _get_subtitle_url(self, sub_lang, sub_name, video_id, format):
"""returns the url for the given subtitle. Redefine in subclasses."""
pass
def _request_automatic_caption(self, video_id, webpage):
"""Request automatic caption. Redefine in subclasses."""
"""returns a tuple of ... """
# return [(err_msg, None, None)]
pass