[9gag] Fix Extraction (#23022)

This commit is contained in:
DrWursterich 2021-01-19 10:21:37 +01:00 committed by GitHub
parent f9201cef58
commit 1dd12708c2
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 122 additions and 78 deletions

View File

@ -3,102 +3,146 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import str_to_int from ..utils import (
determine_ext,
url_or_none,
int_or_none,
float_or_none,
ExtractorError
)
class NineGagIE(InfoExtractor): class NineGagIE(InfoExtractor):
IE_NAME = '9gag' IE_NAME = '9gag'
_VALID_URL = r'https?://(?:www\.)?9gag(?:\.com/tv|\.tv)/(?:p|embed)/(?P<id>[a-zA-Z0-9]+)(?:/(?P<display_id>[^?#/]+))?' _VALID_URL = r'https?://(?:www\.)?9gag\.com/gag/(?P<id>[a-zA-Z0-9]+)'
_TESTS = [{ _TESTS = [{
'url': 'http://9gag.com/tv/p/Kk2X5/people-are-awesome-2013-is-absolutely-awesome', 'url': 'https://9gag.com/gag/an5Qz5b',
'info_dict': { 'info_dict': {
'id': 'kXzwOKyGlSA', 'id': 'an5Qz5b',
'ext': 'mp4', 'ext': 'webm',
'description': 'This 3-minute video will make you smile and then make you feel untalented and insignificant. Anyway, you should share this awesomeness. (Thanks, Dino!)', 'title': 'Dogs playing tetherball',
'title': '\"People Are Awesome 2013\" Is Absolutely Awesome', 'upload_date': '20191108',
'uploader_id': 'UCdEH6EjDKwtTe-sO2f0_1XA', 'timestamp': 1573243994,
'uploader': 'CompilationChannel', 'age_limit': 0,
'upload_date': '20131110', 'categories': [
'view_count': int, 'Wholesome'
}, ],
'add_ie': ['Youtube'], 'tags': [
'Dog'
]
}
}, { }, {
'url': 'http://9gag.com/tv/p/aKolP3', 'url': 'https://9gag.com/gag/ae5Ag7B',
'info_dict': { 'info_dict': {
'id': 'aKolP3', 'id': 'ae5Ag7B',
'ext': 'mp4', 'ext': 'webm',
'title': 'This Guy Travelled 11 countries In 44 days Just To Make This Amazing Video', 'title': 'Capybara Agility Training',
'description': "I just saw more in 1 minute than I've seen in 1 year. This guy's video is epic!!", 'upload_date': '20191108',
'uploader_id': 'rickmereki', 'timestamp': 1573237208,
'uploader': 'Rick Mereki', 'age_limit': 0,
'upload_date': '20110803', 'categories': [
'view_count': int, 'Awesome'
}, ],
'add_ie': ['Vimeo'], 'tags': [
}, { 'Weimaraner',
'url': 'http://9gag.com/tv/p/KklwM', 'American Pit Bull Terrier'
'only_matching': True, ]
}, { }
'url': 'http://9gag.tv/p/Kk2X5',
'only_matching': True,
}, {
'url': 'http://9gag.com/tv/embed/a5Dmvl',
'only_matching': True,
}] }]
_EXTERNAL_VIDEO_PROVIDER = { _EXTERNAL_VIDEO_PROVIDERS = {
'1': { 'Youtube': 'https://youtube.com/watch?v=%s'
'url': '%s',
'ie_key': 'Youtube',
},
'2': {
'url': 'http://player.vimeo.com/video/%s',
'ie_key': 'Vimeo',
},
'3': {
'url': 'http://instagram.com/p/%s',
'ie_key': 'Instagram',
},
'4': {
'url': 'http://vine.co/v/%s',
'ie_key': 'Vine',
},
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('id') webpage = self._download_webpage(url, video_id)
display_id = mobj.group('display_id') or video_id rawJsonData = self._search_regex(
r'window._config\s*=\s*JSON.parse\(["\']({.+?})["\']\);',
webpage = self._download_webpage(url, display_id) webpage,
'data')
post_view = self._parse_json( rawJsonData = rawJsonData.replace('\\"', '"').replace('\\\\/', '/')
self._search_regex( data = self._parse_json(rawJsonData, video_id)['data']['post']
r'var\s+postView\s*=\s*new\s+app\.PostView\({\s*post:\s*({.+?})\s*,\s*posts:\s*prefetchedCurrentPost',
webpage, 'post view'),
display_id)
ie_key = None
source_url = post_view.get('sourceUrl')
if not source_url:
external_video_id = post_view['videoExternalId']
external_video_provider = post_view['videoExternalProvider']
source_url = self._EXTERNAL_VIDEO_PROVIDER[external_video_provider]['url'] % external_video_id
ie_key = self._EXTERNAL_VIDEO_PROVIDER[external_video_provider]['ie_key']
title = post_view['title']
description = post_view.get('description')
view_count = str_to_int(post_view.get('externalView'))
thumbnail = post_view.get('thumbnail_700w') or post_view.get('ogImageUrl') or post_view.get('thumbnail_300w')
if data['type'] == 'Video':
vid = data['video']['id']
ie_key = data['video']['source'].capitalize()
return { return {
'_type': 'url_transparent', '_type': 'url_transparent',
'url': source_url, 'url': self._EXTERNAL_VIDEO_PROVIDERS[ie_key] % vid,
'ie_key': ie_key, 'ie_key': ie_key,
'id': video_id, 'id': vid,
'display_id': display_id, 'duration': data['video'].get('duration'),
'title': title, 'start_time': data['video'].get('startTs')
'description': description, }
'view_count': view_count,
'thumbnail': thumbnail, if data['type'] == 'EmbedVideo':
vid = data['video']['id']
ie_key = data['video']['source'].capitalize()
return {
'_type': 'url_transparent',
'url': data['video']['embedUrl'],
#'ie_key': vid,
'start_time': data['video'].get('startTs')
}
if data['type'] != 'Animated':
raise ExtractorError(
'The given url does not contain a video',
expected=True)
duration = None
formats = []
thumbnails = []
for key in data['images']:
image = data['images'][key]
if 'duration' in image and duration is None:
duration = int_or_none(image['duration'])
url = url_or_none(image.get('url'))
if url == None:
continue
ext = determine_ext(url)
if ext == 'jpg' or ext == 'png':
thumbnail = {
'url': url,
'width': float_or_none(image.get('width')),
'height': float_or_none(image.get('height'))
}
thumbnails.append(thumbnail)
elif ext == 'webm' or ext == 'mp4':
formats.append({
'format_id': re.sub(r'.*_([^\.]+).(.*)', r'\1_\2', url),
'ext': ext,
'url': url,
'width': float_or_none(image.get('width')),
'height': float_or_none(image.get('height'))
})
section = None
postSection = data.get('postSection')
if postSection != None and 'name' in postSection:
section = re.sub(r'\\[^\\]{5}', '', postSection['name'])
age_limit = int_or_none(data.get('nsfw'))
if age_limit != None:
age_limit = age_limit * 18
tags = None
if 'tags' in data:
tags = []
for tag in data.get('tags') or []:
tags.append(tag.get('key'))
return {
'id': video_id,
'title': data['title'],
'timestamp': int_or_none(data.get('creationTs')),
'duration': duration,
'formats': formats,
'thumbnails': thumbnails,
'like_count': int_or_none(data.get('upVoteCount')),
'dislike_count': int_or_none(data.get('downVoteCount')),
'comment_count': int_or_none(data.get('commentsCount')),
'age_limit': age_limit,
'categories': [section],
'tags': tags,
'is_live': False
} }