aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/common.py2
-rw-r--r--youtube_dl/extractor/snotr.py55
2 files changed, 26 insertions, 31 deletions
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index e68657314..3213abacf 100644
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -69,6 +69,7 @@ class InfoExtractor(object):
* vcodec Name of the video codec in use
* container Name of the container format
* filesize The number of bytes, if known in advance
+ * filesize_approx An estimate for the number of bytes
* player_url SWF Player URL (used for rtmpdump).
* protocol The protocol that will be used for the actual
download, lower-case.
@@ -555,6 +556,7 @@ class InfoExtractor(object):
f.get('abr') if f.get('abr') is not None else -1,
audio_ext_preference,
f.get('filesize') if f.get('filesize') is not None else -1,
+ f.get('filesize_approx') if f.get('filesize_approx') is not None else -1,
f.get('format_id'),
)
formats.sort(key=_formats_key)
diff --git a/youtube_dl/extractor/snotr.py b/youtube_dl/extractor/snotr.py
index f89e81bf3..e762ad8f6 100644
--- a/youtube_dl/extractor/snotr.py
+++ b/youtube_dl/extractor/snotr.py
@@ -4,49 +4,39 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-
from ..utils import (
-
+ float_or_none,
str_to_int,
- parse_iso8601,
-
-
-
+ parse_duration,
)
+
class SnotrIE(InfoExtractor):
_VALID_URL = r'http?://(?:www\.)?snotr\.com/video/(?P<id>\d+)/([\w]+)'
- _TESTS =[ {
+ _TESTS = [{
'url': 'http://www.snotr.com/video/13708/Drone_flying_through_fireworks',
'info_dict': {
'id': '13708',
'ext': 'flv',
'title': 'Drone flying through fireworks!',
'duration': 247,
- 'filesize':12320768
- }
- },
-
-
-
- {
-
+ 'filesize_approx': 98566144,
+ }
+ }, {
'url': 'http://www.snotr.com/video/530/David_Letteman_-_George_W_Bush_Top_10',
'info_dict': {
'id': '530',
'ext': 'flv',
'title': 'David Letteman - George W. Bush Top 10',
'duration': 126,
- 'filesize': 1048576
- }
- }]
-
+ 'filesize_approx': 8912896,
+ }
+ }]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
- # TODO more code goes here, for example ...
webpage = self._download_webpage(url, video_id)
title = self._og_search_title(webpage)
@@ -54,20 +44,23 @@ class SnotrIE(InfoExtractor):
video_url = "http://cdn.videos.snotr.com/%s.flv" % video_id
- view_count = str_to_int(self._html_search_regex(r'<p>\n<strong>Views:</strong>\n([\d,\.]+)</p>',webpage,'view count'))
+ view_count = str_to_int(self._html_search_regex(
+ r'<p>\n<strong>Views:</strong>\n([\d,\.]+)</p>',
+ webpage, 'view count', fatal=False))
- duration = self._html_search_regex(r'<p>\n<strong>Length:</strong>\n(.*?)</p>',webpage,'duration')
- duration = str_to_int(duration[:1])*60 + str_to_int(duration[2:4])
+ duration = parse_duration(self._html_search_regex(
+ r'<p>\n<strong>Length:</strong>\n\s*([0-9:]+).*?</p>',
+ webpage, 'duration', fatal=False))
- file_size = self._html_search_regex(r'<p>\n<strong>Filesize:</strong>\n(.*?)</p>',webpage,'filesize')
- file_size = str_to_int(re.match(r'\d+',file_size).group())*131072
+ filesize_approx = float_or_none(self._html_search_regex(
+ r'<p>\n<strong>Filesize:</strong>\n\s*([0-9.]+)\s*megabyte</p>',
+ webpage, 'filesize', fatal=False), invscale=1024 * 1024)
return {
'id': video_id,
'title': title,
- 'url':video_url,
- 'view_count':view_count,
- 'duration':duration,
- 'filesize':file_size
-
- } \ No newline at end of file
+ 'url': video_url,
+ 'view_count': view_count,
+ 'duration': duration,
+ 'filesize_approx': filesize_approx,
+ }