Fix "invalid escape sequences" error on Python 3.6
[youtube-dl] / youtube_dl / extractor / ruutu.py
index e346434f94a585b86b01ddd5c6ae6f7ac3490541..f12bc56141c7512f0f5af750b43ff383e729b637 100644 (file)
@@ -3,86 +3,118 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..compat import compat_urllib_parse_urlparse
-import re
+from ..utils import (
+    determine_ext,
+    ExtractorError,
+    int_or_none,
+    xpath_attr,
+    xpath_text,
+)
 
 
 class RuutuIE(InfoExtractor):
-    _VALID_URL = r'http://(www\.)?ruutu\.fi/ohjelmat/(?:[^/]+/)?(?P<id>.*)$'
+    _VALID_URL = r'https?://(?:www\.)?(?:ruutu|supla)\.fi/(?:video|supla)/(?P<id>\d+)'
     _TESTS = [
         {
-            'url': 'http://www.ruutu.fi/ohjelmat/oletko-aina-halunnut-tietaa-mita-tapahtuu-vain-hetki-ennen-lahetysta-nyt-se-selvisi',
+            'url': 'http://www.ruutu.fi/video/2058907',
             'md5': 'ab2093f39be1ca8581963451b3c0234f',
             'info_dict': {
-                'id': 'oletko-aina-halunnut-tietaa-mita-tapahtuu-vain-hetki-ennen-lahetysta-nyt-se-selvisi',
+                'id': '2058907',
                 'ext': 'mp4',
                 'title': 'Oletko aina halunnut tietää mitä tapahtuu vain hetki ennen lähetystä? - Nyt se selvisi!',
-                'description': 'Toinen toistaan huikeampia ohjelmaideoita ja täysin päätöntä sekoilua? No sitä juuri nimenomaan. Metro Helsingin Iltapäivän vieraaksi saapui Tuomas Kauhanen ja he Petra Kalliomaan kanssa keskustelivat hieman ennen lähetyksen alkua, mutta kamerat olivatkin jo päällä.',
+                'description': 'md5:cfc6ccf0e57a814360df464a91ff67d6',
+                'thumbnail': r're:^https?://.*\.jpg$',
+                'duration': 114,
+                'age_limit': 0,
             },
-            'params': {
-                'format': 'http-1000',
-            }
         },
         {
-            'url': 'http://www.ruutu.fi/ohjelmat/superpesis/superpesis-katso-koko-kausi-ruudussa',
+            'url': 'http://www.ruutu.fi/video/2057306',
             'md5': '065a10ae4d5b8cfd9d0c3d332465e3d9',
             'info_dict': {
-                'id': 'superpesis-katso-koko-kausi-ruudussa',
+                'id': '2057306',
                 'ext': 'mp4',
                 'title': 'Superpesis: katso koko kausi Ruudussa',
-                'description': 'Huippujännittävän Superpesiksen suoria ottelulähetyksiä seurataan Ruudussa kauden alusta viimeiseen finaaliin asti. Katso lisätiedot osoitteesta ruutu.fi/superpesis.',
+                'description': 'md5:bfb7336df2a12dc21d18fa696c9f8f23',
+                'thumbnail': r're:^https?://.*\.jpg$',
+                'duration': 40,
+                'age_limit': 0,
+            },
+        },
+        {
+            'url': 'http://www.supla.fi/supla/2231370',
+            'md5': 'df14e782d49a2c0df03d3be2a54ef949',
+            'info_dict': {
+                'id': '2231370',
+                'ext': 'mp4',
+                'title': 'Osa 1: Mikael Jungner',
+                'description': 'md5:7d90f358c47542e3072ff65d7b1bcffe',
+                'thumbnail': r're:^https?://.*\.jpg$',
+                'age_limit': 0,
             },
-            'params': {
-                'format': 'http-1000',
-            }
         },
     ]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
 
-        video_id = mobj.group('id')
-        webpage = self._download_webpage(url, video_id)
-        media_id = self._html_search_regex(r'data-media-id="(\d+)"', webpage, 'media_id')
-        media_json = self._parse_json(self._search_regex(r'jQuery.extend\([^,]+, (.*)\);', webpage, 'media_data'), video_id)
-        xml_url = media_json['ruutuplayer']['xmlUrl'].replace('{ID}', media_id)
-        media_xml = self._download_xml(xml_url, media_id)
+        video_xml = self._download_xml(
+            'http://gatling.ruutu.fi/media-xml-cache?id=%s' % video_id, video_id)
 
         formats = []
-        parsed_urls = []
-        for fmt in media_xml.findall('.//Clip//'):
-            url = fmt.text
-            if not fmt.tag.endswith('File') or url in parsed_urls or \
-                    'NOT_USED' in url:
-                continue
+        processed_urls = []
+
+        def extract_formats(node):
+            for child in node:
+                if child.tag.endswith('Files'):
+                    extract_formats(child)
+                elif child.tag.endswith('File'):
+                    video_url = child.text
+                    if (not video_url or video_url in processed_urls or
+                            any(p in video_url for p in ('NOT_USED', 'NOT-USED'))):
+                        return
+                    processed_urls.append(video_url)
+                    ext = determine_ext(video_url)
+                    if ext == 'm3u8':
+                        formats.extend(self._extract_m3u8_formats(
+                            video_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
+                    elif ext == 'f4m':
+                        formats.extend(self._extract_f4m_formats(
+                            video_url, video_id, f4m_id='hds', fatal=False))
+                    else:
+                        proto = compat_urllib_parse_urlparse(video_url).scheme
+                        if not child.tag.startswith('HTTP') and proto != 'rtmp':
+                            continue
+                        preference = -1 if proto == 'rtmp' else 1
+                        label = child.get('label')
+                        tbr = int_or_none(child.get('bitrate'))
+                        format_id = '%s-%s' % (proto, label if label else tbr) if label or tbr else proto
+                        if not self._is_valid_url(video_url, video_id, format_id):
+                            continue
+                        width, height = [int_or_none(x) for x in child.get('resolution', 'x').split('x')[:2]]
+                        formats.append({
+                            'format_id': format_id,
+                            'url': video_url,
+                            'width': width,
+                            'height': height,
+                            'tbr': tbr,
+                            'preference': preference,
+                        })
+
+        extract_formats(video_xml.find('./Clip'))
+
+        drm = xpath_text(video_xml, './Clip/DRM', default=None)
+        if not formats and drm:
+            raise ExtractorError('This video is DRM protected.', expected=True)
 
-            if url.endswith('m3u8'):
-                formats.extend(self._extract_m3u8_formats(url, media_id, m3u8_id='hls'))
-                parsed_urls.append(url)
-            elif url.endswith('f4m'):
-                formats.extend(self._extract_f4m_formats(url, media_id, f4m_id='hds'))
-                parsed_urls.append(url)
-            else:
-                proto = compat_urllib_parse_urlparse(url).scheme
-                width_str, height_str = fmt.get('resolution').split('x')
-                tbr = int(fmt.get('bitrate', 0))
-                formats.append({
-                    'format_id': '%s-%d' % (proto, tbr),
-                    'url': url,
-                    'width': int(width_str),
-                    'height': int(height_str),
-                    'tbr': tbr,
-                    'ext': url.rsplit('.', 1)[-1],
-                    'live': True,
-                    'protocol': proto,
-                })
         self._sort_formats(formats)
 
         return {
             'id': video_id,
-            'title': self._og_search_title(webpage),
+            'title': xpath_attr(video_xml, './/Behavior/Program', 'program_name', 'title', fatal=True),
+            'description': xpath_attr(video_xml, './/Behavior/Program', 'description', 'description'),
+            'thumbnail': xpath_attr(video_xml, './/Behavior/Startpicture', 'href', 'thumbnail'),
+            'duration': int_or_none(xpath_text(video_xml, './/Runtime', 'duration')),
+            'age_limit': int_or_none(xpath_text(video_xml, './/AgeLimit', 'age limit')),
             'formats': formats,
-            'description': self._og_search_description(webpage),
-            'thumbnail': self._og_search_thumbnail(webpage),
-            'duration': int(media_xml.find('.//Runtime').text),
-            'age_limit': int(media_xml.find('.//AgeLimit').text),
         }