diff options
Diffstat (limited to 'hypervideo_dl/extractor/duboku.py')
| -rw-r--r-- | hypervideo_dl/extractor/duboku.py | 53 |
1 files changed, 26 insertions, 27 deletions
diff --git a/hypervideo_dl/extractor/duboku.py b/hypervideo_dl/extractor/duboku.py index a875978..fb0546c 100644 --- a/hypervideo_dl/extractor/duboku.py +++ b/hypervideo_dl/extractor/duboku.py @@ -1,6 +1,3 @@ -# coding: utf-8 -from __future__ import unicode_literals - import re from .common import InfoExtractor @@ -54,31 +51,39 @@ def _get_element_by_tag_and_attrib(html, tag=None, attribute=None, value=None, e class DubokuIE(InfoExtractor): IE_NAME = 'duboku' - IE_DESC = 'www.duboku.co' + IE_DESC = 'www.duboku.io' - _VALID_URL = r'(?:https?://[^/]+\.duboku\.co/vodplay/)(?P<id>[0-9]+-[0-9-]+)\.html.*' + _VALID_URL = r'(?:https?://[^/]+\.duboku\.io/vodplay/)(?P<id>[0-9]+-[0-9-]+)\.html.*' _TESTS = [{ - 'url': 'https://www.duboku.co/vodplay/1575-1-1.html', + 'url': 'https://w.duboku.io/vodplay/1575-1-1.html', 'info_dict': { 'id': '1575-1-1', - 'ext': 'ts', + 'ext': 'mp4', 'series': '白色月光', 'title': 'contains:白色月光', 'season_number': 1, 'episode_number': 1, + 'season': 'Season 1', + 'episode_id': '1', + 'season_id': '1', + 'episode': 'Episode 1', }, 'params': { 'skip_download': 'm3u8 download', }, }, { - 'url': 'https://www.duboku.co/vodplay/1588-1-1.html', + 'url': 'https://w.duboku.io/vodplay/1588-1-1.html', 'info_dict': { 'id': '1588-1-1', - 'ext': 'ts', + 'ext': 'mp4', 'series': '亲爱的自己', - 'title': 'contains:预告片', + 'title': 'contains:第1集', 'season_number': 1, 'episode_number': 1, + 'episode': 'Episode 1', + 'season': 'Season 1', + 'episode_id': '1', + 'season_id': '1', }, 'params': { 'skip_download': 'm3u8 download', @@ -94,7 +99,7 @@ class DubokuIE(InfoExtractor): season_id = temp[1] episode_id = temp[2] - webpage_url = 'https://www.duboku.co/vodplay/%s.html' % video_id + webpage_url = 'https://w.duboku.io/vodplay/%s.html' % video_id webpage_html = self._download_webpage(webpage_url, video_id) # extract video url @@ -127,12 +132,13 @@ class DubokuIE(InfoExtractor): data_from = player_data.get('from') # if it is an embedded iframe, maybe it's an external source + headers = {'Referer': webpage_url} if data_from == 'iframe': # use _type url_transparent to retain the meaningful details # of the video. return { '_type': 'url_transparent', - 'url': smuggle_url(data_url, {'http_headers': {'Referer': webpage_url}}), + 'url': smuggle_url(data_url, {'http_headers': headers}), 'id': video_id, 'title': title, 'series': series_title, @@ -142,7 +148,7 @@ class DubokuIE(InfoExtractor): 'episode_id': episode_id, } - formats = self._extract_m3u8_formats(data_url, video_id, 'mp4') + formats = self._extract_m3u8_formats(data_url, video_id, 'mp4', headers=headers) return { 'id': video_id, @@ -153,36 +159,29 @@ class DubokuIE(InfoExtractor): 'episode_number': int_or_none(episode_id), 'episode_id': episode_id, 'formats': formats, - 'http_headers': {'Referer': 'https://www.duboku.co/static/player/videojs.html'} + 'http_headers': headers } class DubokuPlaylistIE(InfoExtractor): IE_NAME = 'duboku:list' - IE_DESC = 'www.duboku.co entire series' + IE_DESC = 'www.duboku.io entire series' - _VALID_URL = r'(?:https?://[^/]+\.duboku\.co/voddetail/)(?P<id>[0-9]+)\.html.*' + _VALID_URL = r'(?:https?://[^/]+\.duboku\.io/voddetail/)(?P<id>[0-9]+)\.html.*' _TESTS = [{ - 'url': 'https://www.duboku.co/voddetail/1575.html', + 'url': 'https://w.duboku.io/voddetail/1575.html', 'info_dict': { 'id': 'startswith:1575', 'title': '白色月光', }, 'playlist_count': 12, }, { - 'url': 'https://www.duboku.co/voddetail/1554.html', + 'url': 'https://w.duboku.io/voddetail/1554.html', 'info_dict': { 'id': 'startswith:1554', 'title': '以家人之名', }, 'playlist_mincount': 30, - }, { - 'url': 'https://www.duboku.co/voddetail/1554.html#playlist2', - 'info_dict': { - 'id': '1554#playlist2', - 'title': '以家人之名', - }, - 'playlist_mincount': 27, }] def _real_extract(self, url): @@ -192,7 +191,7 @@ class DubokuPlaylistIE(InfoExtractor): series_id = mobj.group('id') fragment = compat_urlparse.urlparse(url).fragment - webpage_url = 'https://www.duboku.co/voddetail/%s.html' % series_id + webpage_url = 'https://w.duboku.io/voddetail/%s.html' % series_id webpage_html = self._download_webpage(webpage_url, series_id) # extract title @@ -237,6 +236,6 @@ class DubokuPlaylistIE(InfoExtractor): # return url results return self.playlist_result([ self.url_result( - compat_urlparse.urljoin('https://www.duboku.co', x['href']), + compat_urlparse.urljoin('https://w.duboku.io', x['href']), ie=DubokuIE.ie_key(), video_title=x.get('title')) for x in playlist], series_id + '#' + playlist_id, title) |