]>
Commit | Line | Data |
---|---|---|
289ef490 | 1 | from .common import InfoExtractor |
289ef490 | 2 | from ..utils import ( |
289ef490 | 3 | ExtractorError, |
e897bd82 | 4 | clean_html, |
289ef490 AF |
5 | int_or_none, |
6 | merge_dicts, | |
73c19aaa | 7 | parse_count, |
289ef490 | 8 | str_or_none, |
289ef490 AF |
9 | try_get, |
10 | unified_strdate, | |
11 | urlencode_postdata, | |
12 | urljoin, | |
13 | ) | |
14 | ||
15 | ||
16 | class HKETVIE(InfoExtractor): | |
17 | IE_NAME = 'hketv' | |
18 | IE_DESC = '香港教育局教育電視 (HKETV) Educational Television, Hong Kong Educational Bureau' | |
19 | _GEO_BYPASS = False | |
20 | _GEO_COUNTRIES = ['HK'] | |
21 | _VALID_URL = r'https?://(?:www\.)?hkedcity\.net/etv/resource/(?P<id>[0-9]+)' | |
22 | _TESTS = [{ | |
23 | 'url': 'https://www.hkedcity.net/etv/resource/2932360618', | |
24 | 'md5': 'f193712f5f7abb208ddef3c5ea6ed0b7', | |
25 | 'info_dict': { | |
26 | 'id': '2932360618', | |
27 | 'ext': 'mp4', | |
28 | 'title': '喜閱一生(共享閱讀樂) (中、英文字幕可供選擇)', | |
73c19aaa | 29 | 'description': 'md5:d5286d05219ef50e0613311cbe96e560', |
289ef490 AF |
30 | 'upload_date': '20181024', |
31 | 'duration': 900, | |
73c19aaa | 32 | 'subtitles': 'count:2', |
289ef490 | 33 | }, |
73c19aaa | 34 | 'skip': 'Geo restricted to HK', |
289ef490 AF |
35 | }, { |
36 | 'url': 'https://www.hkedcity.net/etv/resource/972641418', | |
37 | 'md5': '1ed494c1c6cf7866a8290edad9b07dc9', | |
38 | 'info_dict': { | |
39 | 'id': '972641418', | |
40 | 'ext': 'mp4', | |
41 | 'title': '衣冠楚楚 (天使系列之一)', | |
73c19aaa | 42 | 'description': 'md5:10bb3d659421e74f58e5db5691627b0f', |
289ef490 AF |
43 | 'upload_date': '20070109', |
44 | 'duration': 907, | |
45 | 'subtitles': {}, | |
46 | }, | |
73c19aaa | 47 | 'skip': 'Geo restricted to HK', |
289ef490 AF |
48 | }] |
49 | ||
50 | _CC_LANGS = { | |
51 | '中文(繁體中文)': 'zh-Hant', | |
52 | '中文(简体中文)': 'zh-Hans', | |
53 | 'English': 'en', | |
54 | 'Bahasa Indonesia': 'id', | |
55 | '\u0939\u093f\u0928\u094d\u0926\u0940': 'hi', | |
56 | '\u0928\u0947\u092a\u093e\u0932\u0940': 'ne', | |
57 | 'Tagalog': 'tl', | |
58 | '\u0e44\u0e17\u0e22': 'th', | |
59 | '\u0627\u0631\u062f\u0648': 'ur', | |
60 | } | |
73c19aaa S |
61 | _FORMAT_HEIGHTS = { |
62 | 'SD': 360, | |
63 | 'HD': 720, | |
64 | } | |
65 | _APPS_BASE_URL = 'https://apps.hkedcity.net' | |
289ef490 AF |
66 | |
67 | def _real_extract(self, url): | |
68 | video_id = self._match_id(url) | |
69 | webpage = self._download_webpage(url, video_id) | |
289ef490 | 70 | |
73c19aaa S |
71 | title = ( |
72 | self._html_search_meta( | |
3089bc74 S |
73 | ('ed_title', 'search.ed_title'), webpage, default=None) |
74 | or self._search_regex( | |
73c19aaa | 75 | r'data-favorite_title_(?:eng|chi)=(["\'])(?P<id>(?:(?!\1).)+)\1', |
3089bc74 S |
76 | webpage, 'title', default=None, group='url') |
77 | or self._html_search_regex( | |
78 | r'<h1>([^<]+)</h1>', webpage, 'title', default=None) | |
79 | or self._og_search_title(webpage) | |
73c19aaa S |
80 | ) |
81 | ||
82 | file_id = self._search_regex( | |
83 | r'post_var\[["\']file_id["\']\s*\]\s*=\s*(.+?);', | |
84 | webpage, 'file ID') | |
85 | curr_url = self._search_regex( | |
86 | r'post_var\[["\']curr_url["\']\s*\]\s*=\s*"(.+?)";', | |
87 | webpage, 'curr URL') | |
289ef490 AF |
88 | data = { |
89 | 'action': 'get_info', | |
90 | 'curr_url': curr_url, | |
91 | 'file_id': file_id, | |
92 | 'video_url': file_id, | |
93 | } | |
289ef490 AF |
94 | |
95 | response = self._download_json( | |
73c19aaa | 96 | self._APPS_BASE_URL + '/media/play/handler.php', video_id, |
289ef490 | 97 | data=urlencode_postdata(data), |
73c19aaa S |
98 | headers=merge_dicts({ |
99 | 'Content-Type': 'application/x-www-form-urlencoded'}, | |
100 | self.geo_verification_headers())) | |
289ef490 AF |
101 | |
102 | result = response['result'] | |
103 | ||
73c19aaa S |
104 | if not response.get('success') or not response.get('access'): |
105 | error = clean_html(response.get('access_err_msg')) | |
106 | if 'Video streaming is not available in your country' in error: | |
107 | self.raise_geo_restricted( | |
108 | msg=error, countries=self._GEO_COUNTRIES) | |
109 | else: | |
110 | raise ExtractorError(error, expected=True) | |
111 | ||
289ef490 | 112 | formats = [] |
289ef490 | 113 | |
73c19aaa S |
114 | width = int_or_none(result.get('width')) |
115 | height = int_or_none(result.get('height')) | |
116 | ||
117 | playlist0 = result['playlist'][0] | |
118 | for fmt in playlist0['sources']: | |
119 | file_url = urljoin(self._APPS_BASE_URL, fmt.get('file')) | |
120 | if not file_url: | |
121 | continue | |
122 | # If we ever wanted to provide the final resolved URL that | |
123 | # does not require cookies, albeit with a shorter lifespan: | |
124 | # urlh = self._downloader.urlopen(file_url) | |
3d2623a8 | 125 | # resolved_url = urlh.url |
73c19aaa S |
126 | label = fmt.get('label') |
127 | h = self._FORMAT_HEIGHTS.get(label) | |
128 | w = h * width // height if h and width and height else None | |
129 | formats.append({ | |
130 | 'format_id': label, | |
131 | 'ext': fmt.get('type'), | |
132 | 'url': file_url, | |
133 | 'width': w, | |
134 | 'height': h, | |
135 | }) | |
73c19aaa S |
136 | |
137 | subtitles = {} | |
138 | tracks = try_get(playlist0, lambda x: x['tracks'], list) or [] | |
139 | for track in tracks: | |
140 | if not isinstance(track, dict): | |
141 | continue | |
142 | track_kind = str_or_none(track.get('kind')) | |
add96eb9 | 143 | if not track_kind or not isinstance(track_kind, str): |
73c19aaa S |
144 | continue |
145 | if track_kind.lower() not in ('captions', 'subtitles'): | |
146 | continue | |
147 | track_url = urljoin(self._APPS_BASE_URL, track.get('file')) | |
148 | if not track_url: | |
149 | continue | |
150 | track_label = track.get('label') | |
151 | subtitles.setdefault(self._CC_LANGS.get( | |
152 | track_label, track_label), []).append({ | |
289ef490 AF |
153 | 'url': self._proto_relative_url(track_url), |
154 | 'ext': 'srt', | |
155 | }) | |
156 | ||
289ef490 AF |
157 | # Likes |
158 | emotion = self._download_json( | |
73c19aaa | 159 | 'https://emocounter.hkedcity.net/handler.php', video_id, |
289ef490 AF |
160 | data=urlencode_postdata({ |
161 | 'action': 'get_emotion', | |
162 | 'data[bucket_id]': 'etv', | |
163 | 'data[identifier]': video_id, | |
164 | }), | |
165 | headers={'Content-Type': 'application/x-www-form-urlencoded'}, | |
73c19aaa S |
166 | fatal=False) or {} |
167 | like_count = int_or_none(try_get( | |
168 | emotion, lambda x: x['data']['emotion_data'][0]['count'])) | |
289ef490 AF |
169 | |
170 | return { | |
171 | 'id': video_id, | |
172 | 'title': title, | |
73c19aaa S |
173 | 'description': self._html_search_meta( |
174 | 'description', webpage, fatal=False), | |
175 | 'upload_date': unified_strdate(self._html_search_meta( | |
176 | 'ed_date', webpage, fatal=False), day_first=False), | |
289ef490 AF |
177 | 'duration': int_or_none(result.get('length')), |
178 | 'formats': formats, | |
179 | 'subtitles': subtitles, | |
73c19aaa S |
180 | 'thumbnail': urljoin(self._APPS_BASE_URL, result.get('image')), |
181 | 'view_count': parse_count(result.get('view_count')), | |
289ef490 AF |
182 | 'like_count': like_count, |
183 | } |