[snotr] PEP8 and minor fixes (#3296)

This commit is contained in:
Philipp Hagemeister 2014-07-21 12:02:44 +02:00
parent 199ece7eb8
commit 9732d77ed2
4 changed files with 41 additions and 42 deletions

View File

@ -1197,6 +1197,10 @@ def _format_note(self, fdict):
if res: if res:
res += ', ' res += ', '
res += format_bytes(fdict['filesize']) res += format_bytes(fdict['filesize'])
elif fdict.get('filesize_approx') is not None:
if res:
res += ', '
res += '~' + format_bytes(fdict['filesize_approx'])
return res return res
def list_formats(self, info_dict): def list_formats(self, info_dict):

View File

@ -69,6 +69,7 @@ class InfoExtractor(object):
* vcodec Name of the video codec in use * vcodec Name of the video codec in use
* container Name of the container format * container Name of the container format
* filesize The number of bytes, if known in advance * 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). * player_url SWF Player URL (used for rtmpdump).
* protocol The protocol that will be used for the actual * protocol The protocol that will be used for the actual
download, lower-case. download, lower-case.
@ -555,6 +556,7 @@ def _formats_key(f):
f.get('abr') if f.get('abr') is not None else -1, f.get('abr') if f.get('abr') is not None else -1,
audio_ext_preference, audio_ext_preference,
f.get('filesize') if f.get('filesize') is not None else -1, 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'), f.get('format_id'),
) )
formats.sort(key=_formats_key) formats.sort(key=_formats_key)

View File

@ -4,49 +4,39 @@
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
float_or_none,
str_to_int, str_to_int,
parse_iso8601, parse_duration,
) )
class SnotrIE(InfoExtractor): class SnotrIE(InfoExtractor):
_VALID_URL = r'http?://(?:www\.)?snotr\.com/video/(?P<id>\d+)/([\w]+)' _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', 'url': 'http://www.snotr.com/video/13708/Drone_flying_through_fireworks',
'info_dict': { 'info_dict': {
'id': '13708', 'id': '13708',
'ext': 'flv', 'ext': 'flv',
'title': 'Drone flying through fireworks!', 'title': 'Drone flying through fireworks!',
'duration': 247, 'duration': 247,
'filesize':12320768 'filesize_approx': 98566144,
} }
}, }, {
{
'url': 'http://www.snotr.com/video/530/David_Letteman_-_George_W_Bush_Top_10', 'url': 'http://www.snotr.com/video/530/David_Letteman_-_George_W_Bush_Top_10',
'info_dict': { 'info_dict': {
'id': '530', 'id': '530',
'ext': 'flv', 'ext': 'flv',
'title': 'David Letteman - George W. Bush Top 10', 'title': 'David Letteman - George W. Bush Top 10',
'duration': 126, 'duration': 126,
'filesize': 1048576 'filesize_approx': 8912896,
} }
}] }]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
# TODO more code goes here, for example ...
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = self._og_search_title(webpage) title = self._og_search_title(webpage)
@ -54,20 +44,23 @@ def _real_extract(self, url):
video_url = "http://cdn.videos.snotr.com/%s.flv" % video_id 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 = parse_duration(self._html_search_regex(
duration = str_to_int(duration[:1])*60 + str_to_int(duration[2:4]) 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') filesize_approx = float_or_none(self._html_search_regex(
file_size = str_to_int(re.match(r'\d+',file_size).group())*131072 r'<p>\n<strong>Filesize:</strong>\n\s*([0-9.]+)\s*megabyte</p>',
webpage, 'filesize', fatal=False), invscale=1024 * 1024)
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'url':video_url, 'url': video_url,
'view_count':view_count, 'view_count': view_count,
'duration':duration, 'duration': duration,
'filesize':file_size 'filesize_approx': filesize_approx,
}
}

View File

@ -1193,13 +1193,6 @@ def format_bytes(bytes):
return u'%.2f%s' % (converted, suffix) return u'%.2f%s' % (converted, suffix)
def str_to_int(int_str):
if int_str is None:
return None
int_str = re.sub(r'[,\.]', u'', int_str)
return int(int_str)
def get_term_width(): def get_term_width():
columns = os.environ.get('COLUMNS', None) columns = os.environ.get('COLUMNS', None)
if columns: if columns:
@ -1267,15 +1260,22 @@ def get_method(self):
return "HEAD" return "HEAD"
def int_or_none(v, scale=1, default=None, get_attr=None): def int_or_none(v, scale=1, default=None, get_attr=None, invscale=1):
if get_attr: if get_attr:
if v is not None: if v is not None:
v = getattr(v, get_attr, None) v = getattr(v, get_attr, None)
return default if v is None else (int(v) // scale) return default if v is None else (int(v) * invscale // scale)
def float_or_none(v, scale=1, default=None): def str_to_int(int_str):
return default if v is None else (float(v) / scale) if int_str is None:
return None
int_str = re.sub(r'[,\.]', u'', int_str)
return int(int_str)
def float_or_none(v, scale=1, invscale=1, default=None):
return default if v is None else (float(v) * invscale / scale)
def parse_duration(s): def parse_duration(s):