[snotr] PEP8 and minor fixes (#3296)

diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py
index 3dff723b81fff6947ac8cf08c62a275843f359f9..686988fe5bdaa71f8dd346b3b90795d213b92b7c 100755 (executable)
--- a/youtube_dl/YoutubeDL.py
+++ b/youtube_dl/YoutubeDL.py
@@ -1197,6 +1197,10 @@ class YoutubeDL(object):
             if res:
                 res += ', '
             res += format_bytes(fdict['filesize'])
+        elif fdict.get('filesize_approx') is not None:
+            if res:
+                res += ', '
+            res += '~' + format_bytes(fdict['filesize_approx'])
         return res
 
     def list_formats(self, info_dict):

diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index e68657314ecde5406ec2d27fef005f899341daf1..3213abacfc95f9e9dced77c2b8d9d5eac8e9c335 100644 (file)
--- 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 f89e81bf32035f689fa8adf520055729973ceb18..e762ad8f6b24b12aa87697c6d1abf63a9b6fca27 100644 (file)
--- 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,
+        }

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index 919603c623ed8cd809745c1314442adabf4567c8..bf4d1112f9f62cf6a58a26df3d83bb4326470b1c 100644 (file)
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -1193,13 +1193,6 @@ def format_bytes(bytes):
     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():
     columns = os.environ.get('COLUMNS', None)
     if columns:
@@ -1267,15 +1260,22 @@ class HEADRequest(compat_urllib_request.Request):
         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 v is not 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 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 float_or_none(v, scale=1, default=None):
-    return default if v is None else (float(v) / scale)
+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):