- # Sorted by quality
- _known_formats = ['MP3', 'MP4', 'Mid Quality WMV', 'Mid Quality MP4', 'High Quality WMV', 'High Quality MP4']
-
- def _restore_bytes(self, formatted_size):
- if not formatted_size:
- return 0
- m = re.match(r'^(?P<size>\d+(?:\.\d+)?)\s+(?P<units>[a-zA-Z]+)', formatted_size)
- if not m:
- return 0
- units = m.group('units')
- try:
- exponent = ['B', 'KB', 'MB', 'GB', 'TB', 'PB', 'EB', 'ZB', 'YB'].index(units.upper())
- except ValueError:
- return 0
- size = float(m.group('size'))
- return int(size * (1024 ** exponent))
-
- 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
- '''
- # Extract known formats
- 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': self._restore_bytes(x.group('filesize')), # File size is approximate
- 'preference': self._known_formats.index(x.group('quality')),
- 'vcodec': 'none' if x.group('note') == 'Audio only' else None,
- } for x in list(re.finditer(FORMAT_REGEX, html)) if x.group('quality') in self._known_formats]
-
- 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') if m is not None else None
Rapsys Git / youtubedl / blobdiff