fix TODOs, remove 'unicode', more properties
This commit is contained in:
kjy00302
parent
f4a7e38649
commit
b683cae13f
@ -678,7 +678,7 @@ from .tvc import (
|
||||
from .tvigle import TvigleIE
|
||||
from .tvp import TvpIE, TvpSeriesIE
|
||||
from .tvplay import TVPlayIE
|
||||
from .tvple import tvpleIE
|
||||
from .tvple import TvpleIE
|
||||
from .tweakers import TweakersIE
|
||||
from .twentyfourvideo import TwentyFourVideoIE
|
||||
from .twentytwotracks import (
|
||||
|
||||
@ -3,11 +3,13 @@ from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
import re
|
||||
import time
|
||||
import datetime
|
||||
|
||||
|
||||
class tvpleIE(InfoExtractor):
|
||||
class TvpleIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?P<url>(?:www\.)?tvple\.com/(?P<id>[0-9]+))'
|
||||
_TEST = {
|
||||
_TESTS = [{
|
||||
'url': 'http://tvple.com/311090',
|
||||
'md5': '46329fca94a29b5517a30d7e88f48dbf',
|
||||
'info_dict': {
|
||||
@ -16,32 +18,42 @@ class tvpleIE(InfoExtractor):
|
||||
'uploader': '[디지털 드럭] 나비붙이',
|
||||
'uploader_id': 'jack1609',
|
||||
'title': '팜플렛으로 yee를 연주하는 김병만',
|
||||
'description': '자작입니다. 첫 조교..인가..? 조교라긴 애매하지만, 어쨋든 노래로 만드는 건 이번이 처음입니다.\n원본 영상 출처: https://www.youtube.com/watch?v=E4BPHBL35dE\nyee는 유튜브에 치면 원본 영상이 나오는데 다들 아시죠??? 저작권 문제가 될 경우는 지우겠습니다...\n\n병만로이드라고 불러야 하나??'
|
||||
# TODO more properties, either as:
|
||||
# * A value
|
||||
# * MD5 checksum; start the string with md5:
|
||||
# * A regular expression; start the string with re:
|
||||
# * Any Python type (for example int or float)
|
||||
'description': '자작입니다. 첫 조교..인가..? 조교라긴 애매하지만, 어쨋든 노래로 만드는 건 이번이 처음입니다.\n원본 영상 출처: https://www.youtube.com/watch?v=E4BPHBL35dE\nyee는 유튜브에 치면 원본 영상이 나오는데 다들 아시죠??? 저작권 문제가 될 경우는 지우겠습니다...\n\n병만로이드라고 불러야 하나??',
|
||||
'duration': 9
|
||||
}
|
||||
}
|
||||
}, {
|
||||
'url': 'http://tvple.com/208230',
|
||||
'md5': '98e4f705fbb77b0ad9afe6e86751d89a',
|
||||
'info_dict': {
|
||||
'id': '208230',
|
||||
'ext': 'mp4',
|
||||
'uploader': 'mesenghe',
|
||||
'uploader_id': 'mesenghe',
|
||||
'title': '소환사 협곡의 개새끼',
|
||||
'description': 'http://youtu.be/LGABUervp48\n재밌게 봐라\n유튜브나 네이버 동영상으로 퍼가지 말고\n이젠 롤 관련된 건 안 만든다',
|
||||
'duration': 71
|
||||
}
|
||||
}]
|
||||
|
||||
def _convert_srt_subtitle(self, json, duration):
|
||||
"""convert tvple subtitle to srt subtitle"""
|
||||
sec = []
|
||||
sub = ""
|
||||
timecode = []
|
||||
text = []
|
||||
for i in json:
|
||||
sec.append(int(i))
|
||||
if(i != 'status'):
|
||||
sec.append(int(i))
|
||||
|
||||
sec.sort()
|
||||
for second in sec:
|
||||
msec = []
|
||||
for i in json[unicode(second)]:
|
||||
for i in json[str(second)]:
|
||||
msec.append(int(i))
|
||||
msec.sort()
|
||||
for millisecond in msec:
|
||||
timecode.append("%02d:%02d:%02d,%03d" % (second // 60 // 60, second // 60 % 60, second % 60, millisecond))
|
||||
text.append(json[unicode(second)][unicode(millisecond)].replace('<BR>', '\n').replace(' ', ''))
|
||||
text.append(json[str(second)][str(millisecond)].replace('<BR>', '\n').replace(' ', ''))
|
||||
|
||||
timecode.append("%02d:%02d:%02d,%03d" % (duration // 60 // 60, duration // 60 % 60, duration % 60, int(("%0.3f" % duration)[-3:])))
|
||||
|
||||
@ -50,6 +62,7 @@ class tvpleIE(InfoExtractor):
|
||||
return sub
|
||||
|
||||
def _convert_ass_cloud(self, json, videoid, title, width, height):
|
||||
"""convert tvple cloud to ass subtitle"""
|
||||
sec = []
|
||||
|
||||
asstemp1 = "[Script Info]\nTitle: %s\nScriptType: v4.00+\nWrapStyle: 0\nPlayResX: %d\nPlayResY: %d\nScaledBorderAndShadow: yes\n\n[V4+ Styles]\nFormat: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding\nStyle: Default,Arial,14,&H23FFFFFF,&H000000FF,&HC8000000,&HC8000000,-1,0,0,0,100,100,0,0,1,2,2,5,10,10,10,1\n\n" % (title + '-' + videoid, width, height)
|
||||
@ -76,7 +89,7 @@ class tvpleIE(InfoExtractor):
|
||||
if json['cloud']['read_url'][0] != '':
|
||||
subs['tvple'].append({
|
||||
'ext': 'ass',
|
||||
'data': self._convert_ass_cloud(self._download_json(json['cloud']['read_url'][0], 'cloud_%d' % int(videoid)), videoid, title, width, height)
|
||||
'data': self._convert_ass_cloud(self._download_json(json['cloud']['read_url'], 'cloud_%d' % int(videoid)), videoid, title, width, height)
|
||||
})
|
||||
|
||||
if json['subtitle'] != '':
|
||||
@ -96,22 +109,30 @@ class tvpleIE(InfoExtractor):
|
||||
uploader = re.search(r'personacon-sm".*/>\s*(.*)\s*</a>', webpage).group(1) # username
|
||||
uploader_id = re.search(r'"/ch/(.*)/videos"', webpage).group(1) # userid
|
||||
description = re.search(r'collapse-content linkify mg-top-base break-word">\s*(.*)\s*<button type="button" class="collapse-button', webpage, re.DOTALL).group(1).replace(" <br />", "").replace("<br />", "").replace("\n ", "") # description
|
||||
# point = re.search(r'fa-bar-chart"></i></span>\s*(.*)p\s*</li>', webpage).group(1).replace(",", "") # point?
|
||||
view_count = int(re.search(r'fa-play"></i></span>\s*(.*)\s*</li>', webpage).group(1).replace(",", "")) # played
|
||||
duration = playpage['stream']['duration'] # duration
|
||||
# date = re.search(r'<small>\s*(\d{4}-\d{2}-\d{2}) (\d{1,2}:\d{1,2}:\d{1,2}).*\s*</small>', webpage).group(1).replace("-", "") # date FIXME-sometimes not working
|
||||
# time = re.search(r'<small>\s*(\d{4}-\d{2}-\d{2}) (\d{1,2}:\d{1,2}:\d{1,2}).*\s*</small>', webpage).group(2) # time FIXME-sometimes not working
|
||||
try:
|
||||
comment_count = int(re.search(r'fa-cloud"></i></span>\s*(\d*)개의 구름', webpage).group(1).replace(",", "")) # comment count
|
||||
except AttributeError: # if comment count is zero, tvple print '아직 구름이 없습니다. 첫 구름을 띄워보세요!'
|
||||
comment_count = 0
|
||||
|
||||
duration = int(playpage['stream']['duration']) # duration
|
||||
average_rating = int(re.search(r'fa-bar-chart"></i></span>\s*(.*)p\s*</li>', webpage).group(1).replace(",", "")) # rating
|
||||
like_count = int(re.search(r'찜 하기\n<span class="badge">(\d*)</span>', webpage).group(1)) # liked
|
||||
|
||||
uploadeddatetime = re.search(r'(\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2})에 업로드됨', webpage)
|
||||
timestamp = time.mktime(datetime.datetime.strptime(uploadeddatetime.group(1), '%Y-%m-%d %H:%M:%S').timetuple()) + (60 * 60 * 9) # timestamp + KST(+9)
|
||||
|
||||
categories = re.search(r'badge-info">(.*)</span>', webpage).group(1) # categories
|
||||
tags = re.findall(r'"/tag/(.*)" class="tag user-added">', webpage) # tags
|
||||
tags = re.findall(r'class="tag "\n.*}">(.*)</a>', webpage) # tags
|
||||
|
||||
formats = []
|
||||
for formatid in playpage['stream']['sources']:
|
||||
formats.append({
|
||||
'url': playpage['stream']['sources'][formatid]['urls']['mp4_avc'],
|
||||
'ext': 'mp4', # TODO-if file isn't a mp4?
|
||||
'ext': 'mp4', # tvple using mp4 for main format
|
||||
'format_id': formatid,
|
||||
'width': playpage['stream']['width'],
|
||||
'height': playpage['stream']['height'],
|
||||
'no_resume': True
|
||||
'height': playpage['stream']['height']
|
||||
})
|
||||
|
||||
subtitles = self.extract_subtitles(playpage, title, video_id, duration, playpage['stream']['width'], playpage['stream']['height'])
|
||||
@ -120,16 +141,17 @@ class tvpleIE(InfoExtractor):
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'duration': int(duration),
|
||||
'duration': duration,
|
||||
'uploader': uploader,
|
||||
'uploader_id': uploader_id,
|
||||
'view_count': view_count,
|
||||
# 'comment_count': comment_count,
|
||||
'comment_count': comment_count,
|
||||
'thumbnail': playpage['poster'],
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
'categories': categories,
|
||||
'tags': tags
|
||||
|
||||
# TODO more properties (see youtube_dl/extractor/common.py)
|
||||
'tags': tags,
|
||||
'timestamp': timestamp,
|
||||
'avrage_rating': average_rating,
|
||||
'like_count': like_count
|
||||
}
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user