- def _formats_from_html(self, html):
- FORMAT_REGEX = r'''
- (?x)
- <a\s+href="(?P<url>[^"]+)">(?P<quality>[^<]+)</a>\s*
- <span\s+class="usage">\((?P<note>[^\)]+)\)</span>\s*
- (?:<div\s+class="popup\s+rounded">\s*
- <h3>File\s+size</h3>\s*(?P<filesize>.*?)\s*
- </div>)? # File size part may be missing
- '''
- quality = qualities((
- 'MP3', 'MP4',
- 'Low Quality WMV', 'Low Quality MP4',
- 'Mid Quality WMV', 'Mid Quality MP4',
- 'High Quality WMV', 'High Quality MP4'))
- formats = [{
- 'url': x.group('url'),
- 'format_id': x.group('quality'),
- 'format_note': x.group('note'),
- 'format': '%s (%s)' % (x.group('quality'), x.group('note')),
- 'filesize_approx': parse_filesize(x.group('filesize')),
- 'quality': quality(x.group('quality')),
- 'vcodec': 'none' if x.group('note') == 'Audio only' else None,
- } for x in list(re.finditer(FORMAT_REGEX, html))]
-
- self._sort_formats(formats)
-
- return formats
-
- def _extract_title(self, html):
- title = self._html_search_meta('title', html, 'title')
- if title is None:
- title = self._og_search_title(html)
- TITLE_SUFFIX = ' (Channel 9)'
- if title is not None and title.endswith(TITLE_SUFFIX):
- title = title[:-len(TITLE_SUFFIX)]
- return title
-
- def _extract_description(self, html):
- DESCRIPTION_REGEX = r'''(?sx)
- <div\s+class="entry-content">\s*
- <div\s+id="entry-body">\s*
- (?P<description>.+?)\s*
- </div>\s*
- </div>
- '''
- m = re.search(DESCRIPTION_REGEX, html)
- if m is not None:
- return m.group('description')
- return self._html_search_meta('description', html, 'description')
-
- def _extract_duration(self, html):
- m = re.search(r'"length": *"(?P<hours>\d{2}):(?P<minutes>\d{2}):(?P<seconds>\d{2})"', html)
- return ((int(m.group('hours')) * 60 * 60) + (int(m.group('minutes')) * 60) + int(m.group('seconds'))) if m else None
-
- def _extract_slides(self, html):
- m = re.search(r'<a href="(?P<slidesurl>[^"]+)" class="slides">Slides</a>', html)
- return m.group('slidesurl') if m is not None else None
-
- def _extract_zip(self, html):
- m = re.search(r'<a href="(?P<zipurl>[^"]+)" class="zip">Zip</a>', html)
- return m.group('zipurl') if m is not None else None
-
- def _extract_avg_rating(self, html):
- m = re.search(r'<p class="avg-rating">Avg Rating: <span>(?P<avgrating>[^<]+)</span></p>', html)
- return float(m.group('avgrating')) if m is not None else 0
-
- def _extract_rating_count(self, html):
- m = re.search(r'<div class="rating-count">\((?P<ratingcount>[^<]+)\)</div>', html)
- return int(self._fix_count(m.group('ratingcount'))) if m is not None else 0
-
- def _extract_view_count(self, html):
- m = re.search(r'<li class="views">\s*<span class="count">(?P<viewcount>[^<]+)</span> Views\s*</li>', html)
- return int(self._fix_count(m.group('viewcount'))) if m is not None else 0
-
- def _extract_comment_count(self, html):
- m = re.search(r'<li class="comments">\s*<a href="#comments">\s*<span class="count">(?P<commentcount>[^<]+)</span> Comments\s*</a>\s*</li>', html)
- return int(self._fix_count(m.group('commentcount'))) if m is not None else 0
-
- def _fix_count(self, count):
- return int(str(count).replace(',', '')) if count is not None else None
-
- def _extract_authors(self, html):
- m = re.search(r'(?s)<li class="author">(.*?)</li>', html)
- if m is None:
- return None
- return re.findall(r'<a href="/Niners/[^"]+">([^<]+)</a>', m.group(1))
-
- def _extract_session_code(self, html):
- m = re.search(r'<li class="code">\s*(?P<code>.+?)\s*</li>', html)
- return m.group('code') if m is not None else None
-
- def _extract_session_day(self, html):
- m = re.search(r'<li class="day">\s*<a href="/Events/[^"]+">(?P<day>[^<]+)</a>\s*</li>', html)
- return m.group('day').strip() if m is not None else None
-
- def _extract_session_room(self, html):
- m = re.search(r'<li class="room">\s*(?P<room>.+?)\s*</li>', html)
- return m.group('room') if m is not None else None
-
- def _extract_session_speakers(self, html):
- return re.findall(r'<a href="/Events/Speakers/[^"]+">([^<]+)</a>', html)
-
- def _extract_content(self, html, content_path):
- # Look for downloadable content
- formats = self._formats_from_html(html)
- slides = self._extract_slides(html)
- zip_ = self._extract_zip(html)
-
- # Nothing to download
- if len(formats) == 0 and slides is None and zip_ is None:
- self._downloader.report_warning('None of recording, slides or zip are available for %s' % content_path)
- return
-
- # Extract meta
- title = self._extract_title(html)
- description = self._extract_description(html)
- thumbnail = self._og_search_thumbnail(html)
- duration = self._extract_duration(html)
- avg_rating = self._extract_avg_rating(html)
- rating_count = self._extract_rating_count(html)
- view_count = self._extract_view_count(html)
- comment_count = self._extract_comment_count(html)
-
- common = {
- '_type': 'video',
- 'id': content_path,
- 'description': description,
- 'thumbnail': thumbnail,
- 'duration': duration,
- 'avg_rating': avg_rating,
- 'rating_count': rating_count,
- 'view_count': view_count,
- 'comment_count': comment_count,
- }
-
- result = []
-
- if slides is not None:
- d = common.copy()
- d.update({'title': title + '-Slides', 'url': slides})
- result.append(d)
-
- if zip_ is not None:
- d = common.copy()
- d.update({'title': title + '-Zip', 'url': zip_})
- result.append(d)
-
- if len(formats) > 0:
- d = common.copy()
- d.update({'title': title, 'formats': formats})
- result.append(d)
-
- return result
-
- def _extract_entry_item(self, html, content_path):
- contents = self._extract_content(html, content_path)
- if contents is None:
- return contents
-
- if len(contents) > 1:
- raise ExtractorError('Got more than one entry')
- result = contents[0]
- result['authors'] = self._extract_authors(html)
-
- return result
-
- def _extract_session(self, html, content_path):
- contents = self._extract_content(html, content_path)
- if contents is None:
- return contents
-
- session_meta = {
- 'session_code': self._extract_session_code(html),
- 'session_day': self._extract_session_day(html),
- 'session_room': self._extract_session_room(html),
- 'session_speakers': self._extract_session_speakers(html),
- }
-
- for content in contents:
- content.update(session_meta)
-
- return self.playlist_result(contents)
-
- def _extract_list(self, content_path):
- rss = self._download_xml(self._RSS_URL % content_path, content_path, 'Downloading RSS')
Rapsys Git / youtubedl / blobdiff