jens
/
youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[niconico] Extract more metadata and simplify (Closes #3181)

This commit is contained in:
Sergey M․ 2014-07-04 22:05:46 +07:00
parent 0ff30c5333
commit 15ce1338b4
1 changed files with 31 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

57
youtube_dl/extractor/niconico.py
View File

@ -8,10 +8,10 @@ from ..utils import (
compat_urllib_parse, compat_urllib_parse,
compat_urllib_request, compat_urllib_request,
compat_urlparse, compat_urlparse,
compat_str,
ExtractorError, ExtractorError,
unified_strdate, unified_strdate,
parse_duration,
int_or_none,
) )
@ -30,6 +30,7 @@ class NiconicoIE(InfoExtractor):
'uploader_id': '2698420', 'uploader_id': '2698420',
'upload_date': '20131123', 'upload_date': '20131123',
'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org', 'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
'duration': 33,
}, },
'params': { 'params': {
'username': 'ydl.niconico@gmail.com', 'username': 'ydl.niconico@gmail.com',
@ -37,7 +38,7 @@ class NiconicoIE(InfoExtractor):
}, },
} }
_VALID_URL = r'^https?://(?:www\.|secure\.)?nicovideo\.jp/watch/((?:[a-z][a-z])?[0-9]+)(?:.*)$' _VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/((?:[a-z]{2})?[0-9]+)'
_NETRC_MACHINE = 'niconico' _NETRC_MACHINE = 'niconico'
def _real_initialize(self): def _real_initialize(self):
@ -86,35 +87,39 @@ class NiconicoIE(InfoExtractor):
video_real_url = compat_urlparse.parse_qs(flv_info_webpage)['url'][0] video_real_url = compat_urlparse.parse_qs(flv_info_webpage)['url'][0]
# Start extracting information # Start extracting information
video_title = video_info.find('.//title').text title = video_info.find('.//title').text
video_extension = video_info.find('.//movie_type').text extension = video_info.find('.//movie_type').text
video_format = video_extension.upper() video_format = extension.upper()
video_thumbnail = video_info.find('.//thumbnail_url').text thumbnail = video_info.find('.//thumbnail_url').text
video_description = video_info.find('.//description').text description = video_info.find('.//description').text
video_upload_date = unified_strdate(video_info.find('.//first_retrieve').text.split('+')[0]) upload_date = unified_strdate(video_info.find('.//first_retrieve').text.split('+')[0])
video_view_count = video_info.find('.//view_counter').text view_count = int_or_none(video_info.find('.//view_counter').text)
video_webpage_url = video_info.find('.//watch_url').text comment_count = int_or_none(video_info.find('.//comment_num').text)
duration = parse_duration(video_info.find('.//length').text)
webpage_url = video_info.find('.//watch_url').text
# uploader
# No need to fetch extra resources...new API has field for uploader's name
if video_info.find('.//ch_id') is not None: if video_info.find('.//ch_id') is not None:
video_uploader_id = video_info.find('.//ch_id').text uploader_id = video_info.find('.//ch_id').text
video_uploader = video_info.find('.//ch_name').text uploader = video_info.find('.//ch_name').text
elif video_info.find('.//user_id') is not None: elif video_info.find('.//user_id') is not None:
video_uploader_id = video_info.find('.//user_id').text uploader_id = video_info.find('.//user_id').text
video_uploader = video_info.find('.//user_nickname').text uploader = video_info.find('.//user_nickname').text
else:
uploader_id = uploader = None
return { return {
'id': video_id, 'id': video_id,
'url': video_real_url, 'url': video_real_url,
'title': video_title, 'title': title,
'ext': video_extension, 'ext': extension,
'format': video_format, 'format': video_format,
'thumbnail': video_thumbnail, 'thumbnail': thumbnail,
'description': video_description, 'description': description,
'uploader': video_uploader, 'uploader': uploader,
'upload_date': video_upload_date, 'upload_date': upload_date,
'uploader_id': video_uploader_id, 'uploader_id': uploader_id,
'view_count': video_view_count, 'view_count': view_count,
'webpage_url': video_webpage_url, 'comment_count': comment_count,
'duration': duration,
'webpage_url': webpage_url,
} }