]> Raphaël G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/cda.py
debian/changelog: Wrap long line.
[youtubedl] / youtube_dl / extractor / cda.py
old mode 100755 (executable)
new mode 100644 (file)
index 8af3187..0c3af23
@@ -1,18 +1,24 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import codecs
 import re
 
 from .common import InfoExtractor
 from ..utils import (
-    decode_packed_codes,
     ExtractorError,
-    parse_duration
+    float_or_none,
+    int_or_none,
+    multipart_encode,
+    parse_duration,
+    random_birthday,
+    urljoin,
 )
 
 
 class CDAIE(InfoExtractor):
     _VALID_URL = r'https?://(?:(?:www\.)?cda\.pl/video|ebd\.cda\.pl/[0-9]+x[0-9]+)/(?P<id>[0-9a-z]+)'
+    _BASE_URL = 'http://www.cda.pl/'
     _TESTS = [{
         'url': 'http://www.cda.pl/video/5749950c',
         'md5': '6f844bf51b15f31fae165365707ae970',
@@ -21,7 +27,11 @@ class CDAIE(InfoExtractor):
             'ext': 'mp4',
             'height': 720,
             'title': 'Oto dlaczego przed zakrętem należy zwolnić.',
-            'duration': 39
+            'description': 'md5:269ccd135d550da90d1662651fcb9772',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'average_rating': float,
+            'duration': 39,
+            'age_limit': 0,
         }
     }, {
         'url': 'http://www.cda.pl/video/57413289',
@@ -30,40 +40,109 @@ class CDAIE(InfoExtractor):
             'id': '57413289',
             'ext': 'mp4',
             'title': 'Lądowanie na lotnisku na Maderze',
-            'duration': 137
+            'description': 'md5:60d76b71186dcce4e0ba6d4bbdb13e1a',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'uploader': 'crash404',
+            'view_count': int,
+            'average_rating': float,
+            'duration': 137,
+            'age_limit': 0,
         }
+    }, {
+        # Age-restricted
+        'url': 'http://www.cda.pl/video/1273454c4',
+        'info_dict': {
+            'id': '1273454c4',
+            'ext': 'mp4',
+            'title': 'Bronson (2008) napisy HD 1080p',
+            'description': 'md5:1b6cb18508daf2dc4e0fa4db77fec24c',
+            'height': 1080,
+            'uploader': 'boniek61',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 5554,
+            'age_limit': 18,
+            'view_count': int,
+            'average_rating': float,
+        },
     }, {
         'url': 'http://ebd.cda.pl/0x0/5749950c',
         'only_matching': True,
     }]
 
+    def _download_age_confirm_page(self, url, video_id, *args, **kwargs):
+        form_data = random_birthday('rok', 'miesiac', 'dzien')
+        form_data.update({'return': url, 'module': 'video', 'module_id': video_id})
+        data, content_type = multipart_encode(form_data)
+        return self._download_webpage(
+            urljoin(url, '/a/validatebirth'), video_id, *args,
+            data=data, headers={
+                'Referer': url,
+                'Content-Type': content_type,
+            }, **kwargs)
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage('http://ebd.cda.pl/0x0/' + video_id, video_id)
+        self._set_cookie('cda.pl', 'cda.player', 'html5')
+        webpage = self._download_webpage(
+            self._BASE_URL + '/video/' + video_id, video_id)
 
         if 'Ten film jest dostępny dla użytkowników premium' in webpage:
             raise ExtractorError('This video is only available for premium users.', expected=True)
 
-        title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title')
+        need_confirm_age = False
+        if self._html_search_regex(r'(<form[^>]+action="/a/validatebirth")',
+                                   webpage, 'birthday validate form', default=None):
+            webpage = self._download_age_confirm_page(
+                url, video_id, note='Confirming age')
+            need_confirm_age = True
 
         formats = []
 
+        uploader = self._search_regex(r'''(?x)
+            <(span|meta)[^>]+itemprop=(["\'])author\2[^>]*>
+            (?:<\1[^>]*>[^<]*</\1>|(?!</\1>)(?:.|\n))*?
+            <(span|meta)[^>]+itemprop=(["\'])name\4[^>]*>(?P<uploader>[^<]+)</\3>
+        ''', webpage, 'uploader', default=None, group='uploader')
+        view_count = self._search_regex(
+            r'Odsłony:(?:\s|&nbsp;)*([0-9]+)', webpage,
+            'view_count', default=None)
+        average_rating = self._search_regex(
+            r'<(?:span|meta)[^>]+itemprop=(["\'])ratingValue\1[^>]*>(?P<rating_value>[0-9.]+)',
+            webpage, 'rating', fatal=False, group='rating_value')
+
         info_dict = {
             'id': video_id,
-            'title': title,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'uploader': uploader,
+            'view_count': int_or_none(view_count),
+            'average_rating': float_or_none(average_rating),
+            'thumbnail': self._og_search_thumbnail(webpage),
             'formats': formats,
             'duration': None,
+            'age_limit': 18 if need_confirm_age else 0,
         }
 
         def extract_format(page, version):
-            unpacked = decode_packed_codes(page)
-            format_url = self._search_regex(
-                r"(?:file|url)\s*:\s*(\\?[\"'])(?P<url>http.+?)\1", unpacked,
-                '%s url' % version, fatal=False, group='url')
-            if not format_url:
+            json_str = self._html_search_regex(
+                r'player_data=(\\?["\'])(?P<player_data>.+?)\1', page,
+                '%s player_json' % version, fatal=False, group='player_data')
+            if not json_str:
                 return
+            player_data = self._parse_json(
+                json_str, '%s player_data' % version, fatal=False)
+            if not player_data:
+                return
+            video = player_data.get('video')
+            if not video or 'file' not in video:
+                self.report_warning('Unable to extract %s version information' % version)
+                return
+            if video['file'].startswith('uggc'):
+                video['file'] = codecs.decode(video['file'], 'rot_13')
+                if video['file'].endswith('adc.mp4'):
+                    video['file'] = video['file'].replace('adc.mp4', '.mp4')
             f = {
-                'url': format_url,
+                'url': video['file'],
             }
             m = re.search(
                 r'<a[^>]+data-quality="(?P<format_id>[^"]+)"[^>]+href="[^"]+"[^>]+class="[^"]*quality-btn-active[^"]*">(?P<height>[0-9]+)p',
@@ -75,22 +154,27 @@ class CDAIE(InfoExtractor):
                 })
             info_dict['formats'].append(f)
             if not info_dict['duration']:
-                info_dict['duration'] = parse_duration(self._search_regex(
-                    r"duration\s*:\s*(\\?[\"'])(?P<duration>.+?)\1",
-                    unpacked, 'duration', fatal=False, group='duration'))
+                info_dict['duration'] = parse_duration(video.get('duration'))
 
         extract_format(webpage, 'default')
 
         for href, resolution in re.findall(
                 r'<a[^>]+data-quality="[^"]+"[^>]+href="([^"]+)"[^>]+class="quality-btn"[^>]*>([0-9]+p)',
                 webpage):
-            webpage = self._download_webpage(
-                href, video_id, 'Downloading %s version information' % resolution, fatal=False)
+            if need_confirm_age:
+                handler = self._download_age_confirm_page
+            else:
+                handler = self._download_webpage
+
+            webpage = handler(
+                self._BASE_URL + href, video_id,
+                'Downloading %s version information' % resolution, fatal=False)
             if not webpage:
                 # Manually report warning because empty page is returned when
                 # invalid version is requested.
                 self.report_warning('Unable to download %s version information' % resolution)
                 continue
+
             extract_format(webpage, resolution)
 
         self._sort_formats(formats)