diff options
| author | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2014-07-28 15:25:56 +0200 |
|---|---|---|
| committer | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2014-07-28 15:32:38 +0200 |
| commit | 31bb8d3f5142f68c9da389caf9fa2356464cc35e (patch) | |
| tree | e85f304a6387d3bd856c66534763b58e0369f52b /youtube_dl/extractor | |
| parent | 4958ae205873980189793885824418533cd27041 (diff) | |
[bloomberg] Extract the available formats (closes #2776)
It uses a helper method in the InfoExtractor class.
The downloader will pick the requested formats using the bitrate in the info dict.
Diffstat (limited to 'youtube_dl/extractor')
| -rw-r--r-- | youtube_dl/extractor/bloomberg.py | 5 | ||||
| -rw-r--r-- | youtube_dl/extractor/common.py | 17 |
2 files changed, 19 insertions, 3 deletions
diff --git a/youtube_dl/extractor/bloomberg.py b/youtube_dl/extractor/bloomberg.py index 25fb79e14..c51a97ce4 100644 --- a/youtube_dl/extractor/bloomberg.py +++ b/youtube_dl/extractor/bloomberg.py @@ -10,7 +10,7 @@ class BloombergIE(InfoExtractor): _TEST = { 'url': 'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html', - 'md5': '7bf08858ff7c203c870e8a6190e221e5', + # The md5 checksum changes 'info_dict': { 'id': 'qurhIVlJSB6hzkVi229d8g', 'ext': 'flv', @@ -31,8 +31,7 @@ class BloombergIE(InfoExtractor): return { 'id': name.split('-')[-1], 'title': title, - 'url': f4m_url, - 'ext': 'flv', + 'formats': self._extract_f4m_formats(f4m_url, name), 'description': self._og_search_description(webpage), 'thumbnail': self._og_search_thumbnail(webpage), } diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 52c00186e..59030e127 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -18,6 +18,7 @@ from ..utils import ( clean_html, compiled_regex_type, ExtractorError, + int_or_none, RegexNotFoundError, sanitize_filename, unescapeHTML, @@ -590,6 +591,22 @@ class InfoExtractor(object): self.to_screen(msg) time.sleep(timeout) + def _extract_f4m_formats(self, manifest_url, video_id): + manifest = self._download_xml(manifest_url, video_id) + + formats = [] + for media_el in manifest.findall('{http://ns.adobe.com/f4m/1.0}media'): + formats.append({ + 'url': manifest_url, + 'ext': 'flv', + 'tbr': int_or_none(media_el.attrib.get('bitrate')), + 'width': int_or_none(media_el.attrib.get('width')), + 'height': int_or_none(media_el.attrib.get('height')), + }) + self._sort_formats(formats) + + return formats + class SearchInfoExtractor(InfoExtractor): """ |