From 319b00d1ace3533a079c8f81e59c639af777cc2c Mon Sep 17 00:00:00 2001 From: Anthony Fok Date: Wed, 9 Jan 2019 19:36:46 -0700 Subject: [PATCH] [hketv] Fix problems @dstftw found in code review, Round 2 --- youtube_dl/extractor/hketv.py | 84 +++++++++++++++++++++++------------ 1 file changed, 56 insertions(+), 28 deletions(-) diff --git a/youtube_dl/extractor/hketv.py b/youtube_dl/extractor/hketv.py index 7b5855f8c..b5790cdee 100644 --- a/youtube_dl/extractor/hketv.py +++ b/youtube_dl/extractor/hketv.py @@ -4,21 +4,24 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..compat import compat_str from ..utils import ( - ExtractorError, - GeoRestrictedError, clean_html, + ExtractorError, int_or_none, merge_dicts, + str_or_none, str_to_int, try_get, unified_strdate, urlencode_postdata, + urljoin, ) class HKETVIE(InfoExtractor): IE_NAME = 'hketv' IE_DESC = '香港教育局教育電視 (HKETV) Educational Television, Hong Kong Educational Bureau' + _GEO_BYPASS = False + _GEO_COUNTRIES = ['HK'] _VALID_URL = r'https?://(?:www\.)?hkedcity\.net/etv/resource/(?P[0-9]+)' _TESTS = [{ 'url': 'https://www.hkedcity.net/etv/resource/2932360618', @@ -26,7 +29,7 @@ class HKETVIE(InfoExtractor): 'info_dict': { 'id': '2932360618', 'ext': 'mp4', - 'title': '喜閱一生(共享閱讀樂)', + '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。', 'upload_date': '20181024', 'duration': 900, @@ -41,6 +44,18 @@ class HKETVIE(InfoExtractor): }], } }, + }, { + 'url': 'https://www.hkedcity.net/etv/resource/972641418', + 'md5': '1ed494c1c6cf7866a8290edad9b07dc9', + 'info_dict': { + 'id': '972641418', + 'ext': 'mp4', + '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。', + 'upload_date': '20070109', + 'duration': 907, + 'subtitles': {}, + }, }] _CC_LANGS = { @@ -77,43 +92,57 @@ class HKETVIE(InfoExtractor): headers=merge_dicts({'Content-Type': 'application/x-www-form-urlencoded'}, self.geo_verification_headers())) - result = response.get('result') + result = response['result'] formats = [] subtitles = {} if response.get('success') and response.get('access'): - width = str_to_int(result.get('width')) - height = str_to_int(result.get('height')) + width = int_or_none(result.get('width')) + height = int_or_none(result.get('height')) playlist0 = try_get(result, lambda x: x['playlist'][0], dict) - fmts = try_get(playlist0, lambda x: x['sources'], list) + fmts = playlist0.get('sources') for fmt in fmts: - label = fmt.get('label') - if label == 'HD': - h = 720 - elif label == 'SD': - h = 360 - w = h * width // height - urlh = self._downloader.urlopen(_APPS_BASE_URL + fmt.get('file')) - formats.append({ - 'format_id': label, - 'ext': fmt.get('type'), - 'url': urlh.geturl(), - 'width': w, - 'height': h, - }) + file_path = fmt.get('file') + if file_path: + file_url = urljoin(_APPS_BASE_URL, file_path) + # If we ever wanted to provide the final resolved URL that + # does not require cookies, albeit with a shorter lifespan: + # urlh = self._downloader.urlopen(file_url) + # resolved_url = urlh.geturl() - tracks = try_get(playlist0, lambda x: x['tracks'], list) + label = fmt.get('label') + w = None + h = None + if label == 'HD': + h = 720 + elif label == 'SD': + h = 360 + if h: + if width and height: + w = h * width // height + else: + w = h * 4 // 3 + + formats.append({ + 'format_id': label, + 'ext': fmt.get('type'), + 'url': file_url, + 'width': w, + 'height': h, + }) + + tracks = playlist0.get('tracks', []) for track in tracks: if not isinstance(track, dict): continue - track_kind = track.get('kind') + 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 = _APPS_BASE_URL + track.get('file') + track_url = urljoin(_APPS_BASE_URL, track.get('file')) if not track_url: continue track_label = track.get('label') @@ -125,7 +154,7 @@ class HKETVIE(InfoExtractor): else: error = clean_html(response.get('access_err_msg')) if 'Video streaming is not available in your country' in error: - raise GeoRestrictedError(error) + self.raise_geo_restricted(msg=error, countries=self._GEO_COUNTRIES) else: raise ExtractorError(error) @@ -140,8 +169,7 @@ class HKETVIE(InfoExtractor): }), headers={'Content-Type': 'application/x-www-form-urlencoded'}, fatal=False) - if emotion.get('result'): - like_count = str_to_int(try_get(emotion, lambda x: x['data']['emotion_data'][0]['count'], str)) + like_count = int_or_none(try_get(emotion, lambda x: x['data']['emotion_data'][0]['count'])) return { 'id': video_id, @@ -151,7 +179,7 @@ class HKETVIE(InfoExtractor): 'duration': int_or_none(result.get('length')), 'formats': formats, 'subtitles': subtitles, - 'thumbnail': _APPS_BASE_URL + result.get('image'), + 'thumbnail': urljoin(_APPS_BASE_URL, result.get('image')), 'view_count': str_to_int(result.get('view_count')), 'like_count': like_count, }