aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/dailymotion.py39
-rw-r--r--youtube_dl/extractor/subtitles.py80
-rw-r--r--youtube_dl/extractor/youtube.py180
3 files changed, 178 insertions, 121 deletions
diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py
index 3c616e089..f7dffd4cc 100644
--- a/youtube_dl/extractor/dailymotion.py
+++ b/youtube_dl/extractor/dailymotion.py
@@ -1,17 +1,40 @@
import re
import json
import itertools
+import socket
from .common import InfoExtractor
+from .subtitles import NoAutoSubtitlesIE
+
from ..utils import (
+ compat_http_client,
+ compat_urllib_error,
compat_urllib_request,
+ compat_str,
get_element_by_attribute,
get_element_by_id,
ExtractorError,
)
-class DailymotionIE(InfoExtractor):
+
+class DailyMotionSubtitlesIE(NoAutoSubtitlesIE):
+
+ 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 {}
+
+class DailymotionIE(DailyMotionSubtitlesIE, InfoExtractor):
"""Information Extractor for Dailymotion"""
_VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/(?:embed/)?video/([^/]+)'
@@ -73,6 +96,19 @@ class DailymotionIE(InfoExtractor):
raise ExtractorError(u'Unable to extract video URL')
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
+
return [{
'id': video_id,
'url': video_url,
@@ -80,6 +116,7 @@ class DailymotionIE(InfoExtractor):
'upload_date': video_upload_date,
'title': self._og_search_title(webpage),
'ext': video_extension,
+ 'subtitles': video_subtitles,
'thumbnail': info['thumbnail_url']
}]
diff --git a/youtube_dl/extractor/subtitles.py b/youtube_dl/extractor/subtitles.py
new file mode 100644
index 000000000..c10cdf266
--- /dev/null
+++ b/youtube_dl/extractor/subtitles.py
@@ -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 _list_available_subtitles(self, video_id):
+ """ outputs the available subtitles for the video """
+ sub_lang_list = self._get_available_subtitles(video_id)
+ sub_lang = ",".join(list(sub_lang_list.keys()))
+ self.to_screen(u'%s: Available subtitles for video: %s' %
+ (video_id, sub_lang))
+
+ def _extract_subtitles(self, video_id):
+ """ returns {sub_lang: sub} or {} if subtitles not found """
+ available_subs_list = self._get_available_subtitles(video_id)
+ if not available_subs_list: # error, it didn't get the available subtitles
+ return {}
+ if self._downloader.params.get('allsubtitles', False):
+ sub_lang_list = available_subs_list
+ else:
+ if self._downloader.params.get('writesubtitles', False):
+ if self._downloader.params.get('subtitleslangs', False):
+ requested_langs = self._downloader.params.get('subtitleslangs')
+ elif 'en' in available_subs_list:
+ requested_langs = ['en']
+ else:
+ requested_langs = [list(available_subs_list.keys())[0]]
+
+ sub_lang_list = {}
+ for sub_lang in requested_langs:
+ if not sub_lang in available_subs_list:
+ self._downloader.report_warning(u'no closed captions found in the specified language "%s"' % sub_lang)
+ continue
+ sub_lang_list[sub_lang] = available_subs_list[sub_lang]
+
+ subtitles = {}
+ for sub_lang, url in sub_lang_list.items():
+ subtitle = self._request_subtitle_url(sub_lang, url)
+ if subtitle:
+ subtitles[sub_lang] = subtitle
+ return subtitles
+
+ def _request_subtitle_url(self, sub_lang, url):
+ """ makes the http request for the subtitle """
+ 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):
+ """ returns {sub_lang: url} or {} if not available """
+ """ Must be redefined by the subclasses """
+ pass
+
+ def _request_automatic_caption(self, video_id, webpage):
+ """ returns {sub_lang: sub} or {} if not available """
+ """ Must be redefined by the subclasses """
+ pass
+
+
+class NoAutoSubtitlesIE(SubtitlesIE):
+ """ A subtitle class for the servers that don't support auto-captions"""
+
+ def _request_automatic_caption(self, video_id, webpage):
+ self._downloader.report_warning(u'Automatic Captions not supported by this server')
+ return {}
diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index 423a5e973..11611f10d 100644
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -7,6 +7,7 @@ import socket
import itertools
from .common import InfoExtractor, SearchInfoExtractor
+from .subtitles import SubtitlesIE
from ..utils import (
compat_http_client,
compat_parse_qs,
@@ -130,7 +131,65 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
return
self._confirm_age()
-class YoutubeIE(YoutubeBaseInfoExtractor):
+class YoutubeSubtitlesIE(SubtitlesIE):
+
+ def _get_available_subtitles(self, video_id):
+ request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % 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 {}
+ lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list)
+
+ sub_lang_list = {}
+ for l in lang_list:
+ lang = l[1]
+ params = compat_urllib_parse.urlencode({
+ 'lang': lang,
+ 'v': video_id,
+ 'fmt': self._downloader.params.get('subtitlesformat'),
+ })
+ url = u'http://www.youtube.com/api/timedtext?' + params
+ sub_lang_list[lang] = url
+ if not sub_lang_list:
+ self._downloader.report_warning(u'video doesn\'t have subtitles')
+ return {}
+ return sub_lang_list
+
+ def _request_automatic_caption(self, video_id, webpage):
+ """We need the webpage for getting the captions url, pass it as an
+ argument to speed up the process."""
+ sub_lang = (self._downloader.params.get('subtitleslangs') or ['en'])[0]
+ sub_format = self._downloader.params.get('subtitlesformat')
+ self.to_screen(u'%s: Looking for automatic captions' % video_id)
+ mobj = re.search(r';ytplayer.config = ({.*?});', webpage)
+ err_msg = u'Couldn\'t find automatic captions for "%s"' % sub_lang
+ if mobj is None:
+ self._downloader.report_warning(err_msg)
+ return {}
+ player_config = json.loads(mobj.group(1))
+ try:
+ args = player_config[u'args']
+ caption_url = args[u'ttsurl']
+ timestamp = args[u'timestamp']
+ params = compat_urllib_parse.urlencode({
+ 'lang': 'en',
+ 'tlang': sub_lang,
+ 'fmt': sub_format,
+ 'ts': timestamp,
+ 'kind': 'asr',
+ })
+ subtitles_url = caption_url + '&' + params
+ sub = self._download_webpage(subtitles_url, video_id, u'Downloading automatic captions')
+ return {sub_lang: sub}
+ # An extractor error can be raise by the download process if there are
+ # no automatic captions but there are subtitles
+ except (KeyError, ExtractorError):
+ self._downloader.report_warning(err_msg)
+ return {}
+
+class YoutubeIE(YoutubeSubtitlesIE, YoutubeBaseInfoExtractor):
IE_DESC = u'YouTube.com'
_VALID_URL = r"""^
(
@@ -397,19 +456,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
"""Report attempt to download video info webpage."""
self.to_screen(u'%s: Downloading video info webpage' % video_id)
- def report_video_subtitles_download(self, video_id):
- """Report attempt to download video info webpage."""
- self.to_screen(u'%s: Checking available subtitles' % video_id)
-
- def report_video_subtitles_request(self, video_id, sub_lang, format):
- """Report attempt to download video info webpage."""
- self.to_screen(u'%s: Downloading video subtitles for %s.%s' % (video_id, sub_lang, format))
-
- 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 report_information_extraction(self, video_id):
"""Report attempt to extract video information."""
self.to_screen(u'%s: Extracting video information' % video_id)
@@ -464,112 +510,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
# Fallback to the other algortihms
return self._decrypt_signature(s)
-
- def _get_available_subtitles(self, video_id):
- self.report_video_subtitles_download(video_id)
- request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % 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 {}
- sub_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list)
- sub_lang_list = dict((l[1], l[0]) for l in sub_lang_list)
- if not sub_lang_list:
- self._downloader.report_warning(u'video doesn\'t have subtitles')
- return {}
- return sub_lang_list
-
- 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 _request_subtitle(self, sub_lang, sub_name, video_id, format):
- """
- Return the subtitle as a string or None if they are not found
- """
- self.report_video_subtitles_request(video_id, sub_lang, format)
- params = compat_urllib_parse.urlencode({
- 'lang': sub_lang,
- 'name': sub_name,
- 'v': video_id,
- 'fmt': format,
- })
- url = 'http://www.youtube.com/api/timedtext?' + params
- 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 _request_automatic_caption(self, video_id, webpage):
- """We need the webpage for getting the captions url, pass it as an
- argument to speed up the process."""
- sub_lang = (self._downloader.params.get('subtitleslangs') or ['en'])[0]
- sub_format = self._downloader.params.get('subtitlesformat')
- self.to_screen(u'%s: Looking for automatic captions' % video_id)
- mobj = re.search(r';ytplayer.config = ({.*?});', webpage)
- err_msg = u'Couldn\'t find automatic captions for "%s"' % sub_lang
- if mobj is None:
- self._downloader.report_warning(err_msg)
- return {}
- player_config = json.loads(mobj.group(1))
- try:
- args = player_config[u'args']
- caption_url = args[u'ttsurl']
- timestamp = args[u'timestamp']
- params = compat_urllib_parse.urlencode({
- 'lang': 'en',
- 'tlang': sub_lang,
- 'fmt': sub_format,
- 'ts': timestamp,
- 'kind': 'asr',
- })
- subtitles_url = caption_url + '&' + params
- sub = self._download_webpage(subtitles_url, video_id, u'Downloading automatic captions')
- return {sub_lang: sub}
- # An extractor error can be raise by the download process if there are
- # no automatic captions but there are subtitles
- except (KeyError, ExtractorError):
- self._downloader.report_warning(err_msg)
- return {}
-
- def _extract_subtitles(self, video_id):
- """
- Return a dictionary: {language: subtitles} or {} if the subtitles
- couldn't be found
- """
- available_subs_list = self._get_available_subtitles(video_id)
- sub_format = self._downloader.params.get('subtitlesformat')
- if not available_subs_list: #There was some error, it didn't get the available subtitles
- return {}
- if self._downloader.params.get('allsubtitles', False):
- sub_lang_list = available_subs_list
- else:
- if self._downloader.params.get('subtitleslangs', False):
- reqested_langs = self._downloader.params.get('subtitleslangs')
- elif 'en' in available_subs_list:
- reqested_langs = ['en']
- else:
- reqested_langs = [list(available_subs_list.keys())[0]]
-
- sub_lang_list = {}
- for sub_lang in reqested_langs:
- if not sub_lang in available_subs_list:
- self._downloader.report_warning(u'no closed captions found in the specified language "%s"' % sub_lang)
- continue
- sub_lang_list[sub_lang] = available_subs_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 _print_formats(self, formats):
print('Available formats:')
for x in formats: