Mirrors
/
youtube-dl
2
1
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[hketv] Improve and simplify (closes #18696)

Browse Source
master-ytdl-org
Sergey M․ 5 years ago
parent 289ef490f7
commit 73c19aaa9f
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 93 additions and 87 deletions
Show Stats Download Patch File Download Diff File

180
youtube_dl/extractor/hketv.py
Unescape Escape View File

@ -8,8 +8,8 @@ from ..utils import (
ExtractorError, ExtractorError,
int_or_none, int_or_none,
merge_dicts, merge_dicts,
parse_count,
str_or_none, str_or_none,
str_to_int,
try_get, try_get,
unified_strdate, unified_strdate,
urlencode_postdata, urlencode_postdata,
@ -30,20 +30,12 @@ class HKETVIE(InfoExtractor):
'id': '2932360618', 'id': '2932360618',
'ext': 'mp4', 'ext': 'mp4',
'title': '喜閱一生(共享閱讀樂) (中、英文字幕可供選擇)', 'title': '喜閱一生(共享閱讀樂) (中、英文字幕可供選擇)',
'description': '本節目輯錄了「閱讀滿Fun嘉年華」和「二○一八響應世界閱讀日――悅愛閱讀・愈讀愈愛」的活動花絮，並由學者、作家、演藝界人士等，分享培養子女閱讀興趣和習慣的方法，以及呼籲大家一同分享閱讀的樂趣。', 'description': 'md5:d5286d05219ef50e0613311cbe96e560',
'upload_date': '20181024', 'upload_date': '20181024',
'duration': 900, 'duration': 900,
'subtitles': { 'subtitles': 'count:2',
'en': [{
'url': 'https://apps.hkedcity.net/media/mediaplayer/caption.php?f=74395&lang=en',
'ext': 'srt',
}],
'zh-Hant': [{
'url': 'https://apps.hkedcity.net/media/mediaplayer/caption.php?f=74395&lang=qmt',
'ext': 'srt',
}],
}
}, },
'skip': 'Geo restricted to HK',
}, { }, {
'url': 'https://www.hkedcity.net/etv/resource/972641418', 'url': 'https://www.hkedcity.net/etv/resource/972641418',
'md5': '1ed494c1c6cf7866a8290edad9b07dc9', 'md5': '1ed494c1c6cf7866a8290edad9b07dc9',
@ -51,11 +43,15 @@ class HKETVIE(InfoExtractor):
'id': '972641418', 'id': '972641418',
'ext': 'mp4', 'ext': 'mp4',
'title': '衣冠楚楚 (天使系列之一)', 'title': '衣冠楚楚 (天使系列之一)',
'description': '天國仙境，有兩位可愛的天使小姐妹。她們對幾千年來天使衣著一成不變頗有不滿。她們下望人世間：只見人們穿著七彩繽紛、款式各異的服裝，漂亮極了。天使姐妹決定下凡考察衣著，以設計天使新裝。 下到人間，姐妹試穿各式各樣的衣著，引發連串奇特有趣的情節：她們穿著校服在街上閒逛時，被女警誤認為逃學而送回學校，到校後又被體育老師誤認為是新同學，匆匆忙忙換上運動服後在操場上大顯神通。她們穿著護士服在醫院散步時，又被誤認為當班護士，而投入追尋失蹤病童、治病救人的工作中去。姐妹倆還到過玩具店，與布娃娃們談論衣著。她們也去過服裝設計學校，被當成小模特兒而試穿各式服裝。最令姐妹倆興奮的是一場盛大的民族服裝表演會。身穿盛裝的十二個民族的少女在台上翩翩起舞，各種服飾七彩繽紛、美不勝收。姐妹們情不自禁地穿上民族服裝，小天使變成了少數民族姑娘……最後天使姐妹回到天上，對於天使究竟穿甚麼樣的衣服好，她們還是拿不定主意。 節目通過天使姐妹的奇特經歷，反復示範各式衣服鞋襪的正確讀音及談論衣著時的常用句式，並以盛大的民族服裝表演活動，帶出有關服裝的文化知識。內容豐富而饒有趣味。', 'description': 'md5:10bb3d659421e74f58e5db5691627b0f',
'upload_date': '20070109', 'upload_date': '20070109',
'duration': 907, 'duration': 907,
'subtitles': {}, 'subtitles': {},
}, },
'params': {
'geo_verification_proxy': '<HK proxy here>',
},
'skip': 'Geo restricted to HK',
}] }]
_CC_LANGS = { _CC_LANGS = {
@ -69,117 +65,127 @@ class HKETVIE(InfoExtractor):
'\u0e44\u0e17\u0e22': 'th', '\u0e44\u0e17\u0e22': 'th',
'\u0627\u0631\u062f\u0648': 'ur', '\u0627\u0631\u062f\u0648': 'ur',
} }
_FORMAT_HEIGHTS = {
'SD': 360,
'HD': 720,
}
_APPS_BASE_URL = 'https://apps.hkedcity.net'
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = self._html_search_meta('ed_title', webpage, fatal=True)
file_id = self._html_search_regex(r'post_var\["file_id"\]\s*=\s*(.+?);', webpage, 'file ID') title = (
curr_url = self._html_search_regex(r'post_var\["curr_url"\]\s*=\s*"(.+?)";', webpage, 'curr URL') self._html_search_meta(
('ed_title', 'search.ed_title'), webpage, default=None) or
self._search_regex(
r'data-favorite_title_(?:eng|chi)=(["\'])(?P<id>(?:(?!\1).)+)\1',
webpage, 'title', default=None, group='url') or
self._html_search_regex(
r'<h1>([^<]+)</h1>', webpage, 'title', default=None) or
self._og_search_title(webpage)
)
file_id = self._search_regex(
r'post_var\[["\']file_id["\']\s*\]\s*=\s*(.+?);',
webpage, 'file ID')
curr_url = self._search_regex(
r'post_var\[["\']curr_url["\']\s*\]\s*=\s*"(.+?)";',
webpage, 'curr URL')
data = { data = {
'action': 'get_info', 'action': 'get_info',
'curr_url': curr_url, 'curr_url': curr_url,
'file_id': file_id, 'file_id': file_id,
'video_url': file_id, 'video_url': file_id,
} }
_APPS_BASE_URL = 'https://apps.hkedcity.net'
handler_url = _APPS_BASE_URL + '/media/play/handler.php'
response = self._download_json( response = self._download_json(
handler_url, video_id, self._APPS_BASE_URL + '/media/play/handler.php', video_id,
data=urlencode_postdata(data), data=urlencode_postdata(data),
headers=merge_dicts({'Content-Type': 'application/x-www-form-urlencoded'}, headers=merge_dicts({
self.geo_verification_headers())) 'Content-Type': 'application/x-www-form-urlencoded'},
self.geo_verification_headers()))
result = response['result'] result = response['result']
if not response.get('success') or not response.get('access'):
error = clean_html(response.get('access_err_msg'))
if 'Video streaming is not available in your country' in error:
self.raise_geo_restricted(
msg=error, countries=self._GEO_COUNTRIES)
else:
raise ExtractorError(error, expected=True)
formats = [] formats = []
subtitles = {}
if response.get('success') and response.get('access'): width = int_or_none(result.get('width'))
width = int_or_none(result.get('width')) height = int_or_none(result.get('height'))
height = int_or_none(result.get('height'))
playlist0 = result['playlist'][0]
playlist0 = try_get(result, lambda x: x['playlist'][0], dict) for fmt in playlist0['sources']:
fmts = playlist0.get('sources') file_url = urljoin(self._APPS_BASE_URL, fmt.get('file'))
for fmt in fmts: if not file_url:
file_path = fmt.get('file') continue
if file_path: # If we ever wanted to provide the final resolved URL that
file_url = urljoin(_APPS_BASE_URL, file_path) # does not require cookies, albeit with a shorter lifespan:
# If we ever wanted to provide the final resolved URL that # urlh = self._downloader.urlopen(file_url)
# does not require cookies, albeit with a shorter lifespan: # resolved_url = urlh.geturl()
# urlh = self._downloader.urlopen(file_url) label = fmt.get('label')
# resolved_url = urlh.geturl() h = self._FORMAT_HEIGHTS.get(label)
w = h * width // height if h and width and height else None
label = fmt.get('label') formats.append({
w = None 'format_id': label,
h = None 'ext': fmt.get('type'),
if label == 'HD': 'url': file_url,
h = 720 'width': w,
elif label == 'SD': 'height': h,
h = 360 })
if h: self._sort_formats(formats)
if width and height:
w = h * width // height subtitles = {}
else: tracks = try_get(playlist0, lambda x: x['tracks'], list) or []
w = h * 4 // 3 for track in tracks:
if not isinstance(track, dict):
formats.append({ continue
'format_id': label, track_kind = str_or_none(track.get('kind'))
'ext': fmt.get('type'), if not track_kind or not isinstance(track_kind, compat_str):
'url': file_url, continue
'width': w, if track_kind.lower() not in ('captions', 'subtitles'):
'height': h, continue
}) track_url = urljoin(self._APPS_BASE_URL, track.get('file'))
if not track_url:
tracks = playlist0.get('tracks', []) continue
for track in tracks: track_label = track.get('label')
if not isinstance(track, dict): subtitles.setdefault(self._CC_LANGS.get(
continue track_label, track_label), []).append({
track_kind = str_or_none(track.get('kind'))
if not track_kind or not isinstance(track_kind, compat_str):
continue
if track_kind.lower() not in ('captions', 'subtitles'):
continue
track_url = urljoin(_APPS_BASE_URL, track.get('file'))
if not track_url:
continue
track_label = track.get('label')
subtitles.setdefault(self._CC_LANGS.get(track_label, track_label), []).append({
'url': self._proto_relative_url(track_url), 'url': self._proto_relative_url(track_url),
'ext': 'srt', 'ext': 'srt',
}) })
else:
error = clean_html(response.get('access_err_msg'))
if 'Video streaming is not available in your country' in error:
self.raise_geo_restricted(msg=error, countries=self._GEO_COUNTRIES)
else:
raise ExtractorError(error)
# Likes # Likes
emotion = self._download_json( emotion = self._download_json(
'https://emocounter.hkedcity.net/handler.php', 'https://emocounter.hkedcity.net/handler.php', video_id,
video_id,
data=urlencode_postdata({ data=urlencode_postdata({
'action': 'get_emotion', 'action': 'get_emotion',
'data[bucket_id]': 'etv', 'data[bucket_id]': 'etv',
'data[identifier]': video_id, 'data[identifier]': video_id,
}), }),
headers={'Content-Type': 'application/x-www-form-urlencoded'}, headers={'Content-Type': 'application/x-www-form-urlencoded'},
fatal=False) fatal=False) or {}
like_count = int_or_none(try_get(emotion, lambda x: x['data']['emotion_data'][0]['count'])) like_count = int_or_none(try_get(
emotion, lambda x: x['data']['emotion_data'][0]['count']))
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'description': self._html_search_meta('description', webpage, fatal=False), 'description': self._html_search_meta(
'upload_date': unified_strdate(self._html_search_meta('ed_date', webpage, fatal=False), day_first=False), 'description', webpage, fatal=False),
'upload_date': unified_strdate(self._html_search_meta(
'ed_date', webpage, fatal=False), day_first=False),
'duration': int_or_none(result.get('length')), 'duration': int_or_none(result.get('length')),
'formats': formats, 'formats': formats,
'subtitles': subtitles, 'subtitles': subtitles,
'thumbnail': urljoin(_APPS_BASE_URL, result.get('image')), 'thumbnail': urljoin(self._APPS_BASE_URL, result.get('image')),
'view_count': str_to_int(result.get('view_count')), 'view_count': parse_count(result.get('view_count')),
'like_count': like_count, 'like_count': like_count,
} }

Write Preview
Loading…
Cancel
Save