]>
Commit | Line | Data |
---|---|---|
503406d4 | 1 | # coding: utf-8 |
2 | from __future__ import unicode_literals | |
3 | ||
4 | import re | |
5 | ||
6 | from .common import InfoExtractor | |
de4144a4 | 7 | from ..compat import compat_urlparse |
7cc9d5b3 | 8 | from ..utils import ( |
9 | clean_html, | |
10 | extract_attributes, | |
11 | ExtractorError, | |
12 | get_elements_by_class, | |
13 | int_or_none, | |
14 | js_to_json, | |
15 | smuggle_url, | |
16 | unescapeHTML, | |
17 | ) | |
503406d4 | 18 | |
19 | ||
de4144a4 | 20 | def _get_elements_by_tag_and_attrib(html, tag=None, attribute=None, value=None, escape_value=True): |
21 | """Return the content of the tag with the specified attribute in the passed HTML document""" | |
22 | ||
23 | if tag is None: | |
24 | tag = '[a-zA-Z0-9:._-]+' | |
25 | if attribute is None: | |
26 | attribute = '' | |
27 | else: | |
28 | attribute = r'\s+(?P<attribute>%s)' % re.escape(attribute) | |
29 | if value is None: | |
30 | value = '' | |
31 | else: | |
32 | value = re.escape(value) if escape_value else value | |
33 | value = '=[\'"]?(?P<value>%s)[\'"]?' % value | |
34 | ||
35 | retlist = [] | |
36 | for m in re.finditer(r'''(?xs) | |
37 | <(?P<tag>%s) | |
38 | (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'|))*? | |
39 | %s%s | |
40 | (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'|))*? | |
41 | \s*> | |
42 | (?P<content>.*?) | |
43 | </\1> | |
44 | ''' % (tag, attribute, value), html): | |
45 | retlist.append(m) | |
46 | ||
47 | return retlist | |
48 | ||
49 | ||
50 | def _get_element_by_tag_and_attrib(html, tag=None, attribute=None, value=None, escape_value=True): | |
51 | retval = _get_elements_by_tag_and_attrib(html, tag, attribute, value, escape_value) | |
52 | return retval[0] if retval else None | |
53 | ||
54 | ||
503406d4 | 55 | class DubokuIE(InfoExtractor): |
de4144a4 | 56 | IE_NAME = 'duboku' |
57 | IE_DESC = 'www.duboku.co' | |
58 | ||
a8f88d2f | 59 | _VALID_URL = r'(?:https?://[^/]+\.duboku\.co/vodplay/)(?P<id>[0-9]+-[0-9-]+)\.html.*' |
503406d4 | 60 | _TESTS = [{ |
61 | 'url': 'https://www.duboku.co/vodplay/1575-1-1.html', | |
62 | 'info_dict': { | |
63 | 'id': '1575-1-1', | |
7cc9d5b3 | 64 | 'ext': 'ts', |
65 | 'series': '白色月光', | |
66 | 'title': 'contains:白色月光', | |
67 | 'season_number': 1, | |
68 | 'episode_number': 1, | |
69 | }, | |
70 | 'params': { | |
71 | 'skip_download': 'm3u8 download', | |
72 | }, | |
73 | }, { | |
74 | 'url': 'https://www.duboku.co/vodplay/1588-1-1.html', | |
75 | 'info_dict': { | |
76 | 'id': '1588-1-1', | |
77 | 'ext': 'ts', | |
78 | 'series': '亲爱的自己', | |
79 | 'title': 'contains:预告片', | |
80 | 'season_number': 1, | |
81 | 'episode_number': 1, | |
503406d4 | 82 | }, |
83 | 'params': { | |
84 | 'skip_download': 'm3u8 download', | |
85 | }, | |
86 | }] | |
87 | ||
88 | _PLAYER_DATA_PATTERN = r'player_data\s*=\s*(\{\s*(.*)})\s*;?\s*</script' | |
89 | ||
90 | def _real_extract(self, url): | |
91 | video_id = self._match_id(url) | |
92 | temp = video_id.split('-') | |
93 | series_id = temp[0] | |
94 | season_id = temp[1] | |
95 | episode_id = temp[2] | |
96 | ||
97 | webpage_url = 'https://www.duboku.co/vodplay/%s.html' % video_id | |
98 | webpage_html = self._download_webpage(webpage_url, video_id) | |
99 | ||
100 | # extract video url | |
101 | ||
102 | player_data = self._search_regex( | |
103 | self._PLAYER_DATA_PATTERN, webpage_html, 'player_data') | |
104 | player_data = self._parse_json(js_to_json(player_data), video_id) | |
105 | ||
106 | # extract title | |
107 | ||
108 | temp = get_elements_by_class('title', webpage_html) | |
109 | series_title = None | |
110 | title = None | |
111 | for html in temp: | |
112 | mobj = re.search(r'<a\s+.*>(.*)</a>', html) | |
113 | if mobj: | |
114 | href = extract_attributes(mobj.group(0)).get('href') | |
115 | if href: | |
116 | mobj1 = re.search(r'/(\d+)\.html', href) | |
117 | if mobj1 and mobj1.group(1) == series_id: | |
118 | series_title = clean_html(mobj.group(0)) | |
119 | series_title = re.sub(r'[\s\r\n\t]+', ' ', series_title) | |
120 | title = clean_html(html) | |
121 | title = re.sub(r'[\s\r\n\t]+', ' ', title) | |
122 | break | |
123 | ||
124 | data_url = player_data['url'] | |
125 | assert data_url | |
126 | data_from = player_data.get('from') | |
127 | ||
128 | # if it is an embedded iframe, maybe it's an external source | |
129 | if data_from == 'iframe': | |
130 | # use _type url_transparent to retain the meaningful details | |
131 | # of the video. | |
132 | return { | |
133 | '_type': 'url_transparent', | |
134 | 'url': smuggle_url(data_url, {'http_headers': {'Referer': webpage_url}}), | |
135 | 'id': video_id, | |
136 | 'title': title, | |
137 | 'series': series_title, | |
138 | 'season_number': int_or_none(season_id), | |
139 | 'season_id': season_id, | |
140 | 'episode_number': int_or_none(episode_id), | |
141 | 'episode_id': episode_id, | |
142 | } | |
143 | ||
144 | formats = self._extract_m3u8_formats(data_url, video_id, 'ts') | |
145 | ||
146 | return { | |
147 | 'id': video_id, | |
148 | 'title': title, | |
149 | 'series': series_title, | |
150 | 'season_number': int_or_none(season_id), | |
151 | 'season_id': season_id, | |
152 | 'episode_number': int_or_none(episode_id), | |
153 | 'episode_id': episode_id, | |
154 | 'formats': formats, | |
155 | } | |
de4144a4 | 156 | |
157 | ||
158 | class DubokuPlaylistIE(InfoExtractor): | |
159 | IE_NAME = 'duboku:list' | |
160 | IE_DESC = 'www.duboku.co entire series' | |
161 | ||
162 | _VALID_URL = r'(?:https?://[^/]+\.duboku\.co/voddetail/)(?P<id>[0-9]+)\.html.*' | |
d82b6697 | 163 | _TESTS = [{ |
7cc9d5b3 | 164 | 'url': 'https://www.duboku.co/voddetail/1575.html', |
d82b6697 | 165 | 'info_dict': { |
7cc9d5b3 | 166 | 'id': 'startswith:1575', |
d82b6697 | 167 | 'title': '白色月光', |
168 | }, | |
169 | 'playlist_count': 12, | |
170 | }, { | |
7cc9d5b3 | 171 | 'url': 'https://www.duboku.co/voddetail/1554.html', |
d82b6697 | 172 | 'info_dict': { |
7cc9d5b3 | 173 | 'id': 'startswith:1554', |
d82b6697 | 174 | 'title': '以家人之名', |
175 | }, | |
7cc9d5b3 | 176 | 'playlist_mincount': 30, |
d82b6697 | 177 | }, { |
7cc9d5b3 | 178 | 'url': 'https://www.duboku.co/voddetail/1554.html#playlist2', |
d82b6697 | 179 | 'info_dict': { |
180 | 'id': '1554#playlist2', | |
181 | 'title': '以家人之名', | |
182 | }, | |
7cc9d5b3 | 183 | 'playlist_mincount': 27, |
d82b6697 | 184 | }] |
de4144a4 | 185 | |
186 | def _real_extract(self, url): | |
187 | mobj = re.match(self._VALID_URL, url) | |
188 | if mobj is None: | |
189 | raise ExtractorError('Invalid URL: %s' % url) | |
190 | series_id = mobj.group('id') | |
191 | fragment = compat_urlparse.urlparse(url).fragment | |
192 | ||
193 | webpage_url = 'https://www.duboku.co/voddetail/%s.html' % series_id | |
194 | webpage_html = self._download_webpage(webpage_url, series_id) | |
195 | ||
196 | # extract title | |
197 | ||
198 | title = _get_element_by_tag_and_attrib(webpage_html, 'h1', 'class', 'title') | |
199 | title = unescapeHTML(title.group('content')) if title else None | |
200 | if not title: | |
201 | title = self._html_search_meta('keywords', webpage_html) | |
202 | if not title: | |
203 | title = _get_element_by_tag_and_attrib(webpage_html, 'title') | |
204 | title = unescapeHTML(title.group('content')) if title else None | |
205 | ||
206 | # extract playlists | |
207 | ||
208 | playlists = {} | |
209 | for div in _get_elements_by_tag_and_attrib( | |
210 | webpage_html, attribute='id', value='playlist\\d+', escape_value=False): | |
211 | playlist_id = div.group('value') | |
212 | playlist = [] | |
213 | for a in _get_elements_by_tag_and_attrib( | |
214 | div.group('content'), 'a', 'href', value='[^\'"]+?', escape_value=False): | |
215 | playlist.append({ | |
216 | 'href': unescapeHTML(a.group('value')), | |
217 | 'title': unescapeHTML(a.group('content')) | |
218 | }) | |
219 | playlists[playlist_id] = playlist | |
220 | ||
221 | # select the specified playlist if url fragment exists | |
d82b6697 | 222 | playlist = None |
223 | playlist_id = None | |
224 | if fragment: | |
225 | playlist = playlists.get(fragment) | |
226 | playlist_id = fragment | |
227 | else: | |
228 | first = next(iter(playlists.items())) | |
229 | if first: | |
230 | (playlist_id, playlist) = first | |
de4144a4 | 231 | if not playlist: |
232 | raise ExtractorError( | |
233 | 'Cannot find %s' % fragment if fragment else 'Cannot extract playlist') | |
234 | ||
235 | # return url results | |
236 | return self.playlist_result([ | |
237 | self.url_result( | |
d82b6697 | 238 | 'https://www.duboku.co' + x['href'], DubokuIE.IE_NAME, video_title=x.get('title')) |
239 | for x in playlist], series_id + '#' + playlist_id, title) |