Fixed for modified embed page for Pakistan users
This is a crude/quick fix for Dailymotion visitors from Pakistan, or any other country which is being served a new "v5Player" embed page. Had to add "fatal=False" in a few places otherwise it won't run, which issues couple of Warnings but otherwise works.
This commit is contained in:
Asadullah-Ahmad
parent
b062d94eef
commit
a742c00965
@ -19,7 +19,6 @@ from ..utils import (
|
|||||||
unescapeHTML,
|
unescapeHTML,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
class DailymotionBaseInfoExtractor(InfoExtractor):
|
class DailymotionBaseInfoExtractor(InfoExtractor):
|
||||||
@staticmethod
|
@staticmethod
|
||||||
def _build_request(url):
|
def _build_request(url):
|
||||||
@ -34,7 +33,6 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
|
|||||||
|
|
||||||
_VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(embed|#)/)?video/(?P<id>[^/?_]+)'
|
_VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(embed|#)/)?video/(?P<id>[^/?_]+)'
|
||||||
IE_NAME = 'dailymotion'
|
IE_NAME = 'dailymotion'
|
||||||
|
|
||||||
_FORMATS = [
|
_FORMATS = [
|
||||||
('stream_h264_ld_url', 'ld'),
|
('stream_h264_ld_url', 'ld'),
|
||||||
('stream_h264_url', 'standard'),
|
('stream_h264_url', 'standard'),
|
||||||
@ -42,7 +40,14 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
|
|||||||
('stream_h264_hd_url', 'hd'),
|
('stream_h264_hd_url', 'hd'),
|
||||||
('stream_h264_hd1080_url', 'hd180'),
|
('stream_h264_hd1080_url', 'hd180'),
|
||||||
]
|
]
|
||||||
|
"""Formats for 'playerv5' pages"""
|
||||||
|
_FORMATSv5 = [
|
||||||
|
('240', 'ld'),
|
||||||
|
('380', 'standard'),
|
||||||
|
('480', 'hq'),
|
||||||
|
('720', 'hd'),
|
||||||
|
('1080', 'hd1080'),
|
||||||
|
]
|
||||||
_TESTS = [
|
_TESTS = [
|
||||||
{
|
{
|
||||||
'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames',
|
'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames',
|
||||||
@ -117,56 +122,99 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
|
|||||||
embed_page = self._download_webpage(
|
embed_page = self._download_webpage(
|
||||||
embed_request, video_id, 'Downloading embed page')
|
embed_request, video_id, 'Downloading embed page')
|
||||||
info = self._search_regex(r'var info = ({.*?}),$', embed_page,
|
info = self._search_regex(r'var info = ({.*?}),$', embed_page,
|
||||||
'video info', flags=re.MULTILINE)
|
'video info', flags=re.MULTILINE, fatal=False)
|
||||||
info = json.loads(info)
|
"""For normal embed pages with info JSON"""
|
||||||
if info.get('error') is not None:
|
if info is not None:
|
||||||
msg = 'Couldn\'t get video, Dailymotion says: %s' % info['error']['title']
|
info = json.loads(info)
|
||||||
raise ExtractorError(msg, expected=True)
|
if info.get('error') is not None:
|
||||||
|
msg = 'Couldn\'t get video, Dailymotion says: %s' % info['error']['title']
|
||||||
formats = []
|
raise ExtractorError(msg, expected=True)
|
||||||
for (key, format_id) in self._FORMATS:
|
formats = []
|
||||||
video_url = info.get(key)
|
for (key, format_id) in self._FORMATS:
|
||||||
if video_url is not None:
|
video_url = info.get(key)
|
||||||
m_size = re.search(r'H264-(\d+)x(\d+)', video_url)
|
if video_url is not None:
|
||||||
if m_size is not None:
|
m_size = re.search(r'H264-(\d+)x(\d+)', video_url)
|
||||||
width, height = map(int_or_none, (m_size.group(1), m_size.group(2)))
|
if m_size is not None:
|
||||||
else:
|
width, height = map(int_or_none, (m_size.group(1), m_size.group(2)))
|
||||||
width, height = None, None
|
else:
|
||||||
formats.append({
|
width, height = None, None
|
||||||
'url': video_url,
|
formats.append({
|
||||||
'ext': 'mp4',
|
'url': video_url,
|
||||||
'format_id': format_id,
|
'ext': 'mp4',
|
||||||
'width': width,
|
'format_id': format_id,
|
||||||
'height': height,
|
'width': width,
|
||||||
})
|
'height': height,
|
||||||
if not formats:
|
})
|
||||||
raise ExtractorError('Unable to extract video URL')
|
if not formats:
|
||||||
|
raise ExtractorError('Unable to extract video URL')
|
||||||
# subtitles
|
video_subtitles = self.extract_subtitles(video_id, webpage)
|
||||||
video_subtitles = self.extract_subtitles(video_id, webpage)
|
view_count = str_to_int(self._search_regex(
|
||||||
|
r'video_views_count[^>]+>\s+([\d\.,]+)',
|
||||||
view_count = str_to_int(self._search_regex(
|
webpage, 'view count', fatal=False))
|
||||||
r'video_views_count[^>]+>\s+([\d\.,]+)',
|
title = self._og_search_title(webpage, default=None)
|
||||||
webpage, 'view count', fatal=False))
|
if title is None:
|
||||||
|
title = self._html_search_regex(
|
||||||
title = self._og_search_title(webpage, default=None)
|
|
||||||
if title is None:
|
|
||||||
title = self._html_search_regex(
|
|
||||||
r'(?s)<span\s+id="video_title"[^>]*>(.*?)</span>', webpage,
|
r'(?s)<span\s+id="video_title"[^>]*>(.*?)</span>', webpage,
|
||||||
'title')
|
'title')
|
||||||
|
return {
|
||||||
return {
|
'id': video_id,
|
||||||
'id': video_id,
|
'formats': formats,
|
||||||
'formats': formats,
|
'uploader': info['owner.screenname'],
|
||||||
'uploader': info['owner.screenname'],
|
'upload_date': video_upload_date,
|
||||||
'upload_date': video_upload_date,
|
'title': title,
|
||||||
'title': title,
|
'subtitles': video_subtitles,
|
||||||
'subtitles': video_subtitles,
|
'thumbnail': info['thumbnail_url'],
|
||||||
'thumbnail': info['thumbnail_url'],
|
'age_limit': age_limit,
|
||||||
'age_limit': age_limit,
|
'view_count': view_count,
|
||||||
'view_count': view_count,
|
'duration': info['duration']
|
||||||
'duration': info['duration']
|
}
|
||||||
}
|
else:
|
||||||
|
formats = []
|
||||||
|
for (key, format_id) in self._FORMATSv5:
|
||||||
|
video_url = self._search_regex(r'%s+".{30}(.*?)"' % key, embed_page,
|
||||||
|
'video info', flags=re.MULTILINE, fatal=False)
|
||||||
|
if video_url:
|
||||||
|
video_url = video_url.replace("\\", "")
|
||||||
|
if video_url is not None:
|
||||||
|
m_size = re.search(r'H264-(\d+)x(\d+)', video_url)
|
||||||
|
if m_size is not None:
|
||||||
|
width, height = map(int_or_none, (m_size.group(1), m_size.group(2)))
|
||||||
|
else:
|
||||||
|
width, height = None, None
|
||||||
|
formats.append({
|
||||||
|
'url': video_url,
|
||||||
|
'ext': 'mp4',
|
||||||
|
'format_id': format_id,
|
||||||
|
'width': width,
|
||||||
|
'height': height,
|
||||||
|
})
|
||||||
|
if not formats:
|
||||||
|
raise ExtractorError('Unable to extract video URL from playerv5 page')
|
||||||
|
v5screenname = self._search_regex(r'screenname":"(.*?)"', embed_page,
|
||||||
|
'video info', flags=re.MULTILINE)
|
||||||
|
v5thumbnailurl = self._search_regex(r'poster_url":"(.*?)"', embed_page,
|
||||||
|
'video info', flags=re.MULTILINE)
|
||||||
|
video_subtitles = self.extract_subtitles(video_id, webpage)
|
||||||
|
view_count = str_to_int(self._search_regex(
|
||||||
|
r'video_views_count[^>]+>\s+([\d\.,]+)',
|
||||||
|
webpage, 'view count', fatal=False))
|
||||||
|
title = self._og_search_title(webpage, default=None)
|
||||||
|
if title is None:
|
||||||
|
title = self._html_search_regex(
|
||||||
|
r'(?s)<span\s+id="video_title"[^>]*>(.*?)</span>', webpage,
|
||||||
|
'title')
|
||||||
|
return {
|
||||||
|
'id': video_id,
|
||||||
|
'formats': formats,
|
||||||
|
'uploader': v5screenname,
|
||||||
|
'upload_date': video_upload_date,
|
||||||
|
'title': self._og_search_title(webpage),
|
||||||
|
'subtitles': video_subtitles,
|
||||||
|
'thumbnail': v5thumbnailurl,
|
||||||
|
'age_limit': age_limit,
|
||||||
|
'view_count': view_count,
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
def _get_subtitles(self, video_id, webpage):
|
def _get_subtitles(self, video_id, webpage):
|
||||||
try:
|
try:
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user