[ie/SnapchatSpotlight] Add extractor (#11030)

Closes #1797
Authored by: seproDev
This commit is contained in:
sepro 2024-09-26 18:32:51 +02:00 committed by GitHub
parent 28b0ecba2a
commit b37417e4f9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 77 additions and 0 deletions

View File

@ -1880,6 +1880,7 @@
from .slideslive import SlidesLiveIE
from .slutload import SlutloadIE
from .smotrim import SmotrimIE
from .snapchat import SnapchatSpotlightIE
from .snotr import SnotrIE
from .sohu import (
SohuIE,

View File

@ -0,0 +1,76 @@
from .common import InfoExtractor
from ..utils import float_or_none, int_or_none, url_or_none
from ..utils.traversal import traverse_obj
class SnapchatSpotlightIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?snapchat\.com/spotlight/(?P<id>\w+)'
_TESTS = [{
'url': 'https://www.snapchat.com/spotlight/W7_EDlXWTBiXAEEniNoMPwAAYYWtidGhudGZpAX1TKn0JAX1TKnXJAAAAAA',
'md5': '46c580f63592d0cbb76e974d2f9f0fcc',
'info_dict': {
'id': 'W7_EDlXWTBiXAEEniNoMPwAAYYWtidGhudGZpAX1TKn0JAX1TKnXJAAAAAA',
'ext': 'mp4',
'title': 'Views 💕',
'description': '',
'thumbnail': r're:https://cf-st\.sc-cdn\.net/d/kKJHIR1QAznRKK9jgYYDq\.256\.IRZXSOY',
'duration': 4.665,
'timestamp': 1637777831.369,
'upload_date': '20211124',
'repost_count': int,
'uploader': 'shreypatel57',
'uploader_url': 'https://www.snapchat.com/add/shreypatel57',
},
}, {
'url': 'https://www.snapchat.com/spotlight/W7_EDlXWTBiXAEEniNoMPwAAYcnVjYWdwcGV1AZEaIYn5AZEaIYnrAAAAAQ',
'md5': '4cd9626458c1a0e3e6dbe72c544a9ec2',
'info_dict': {
'id': 'W7_EDlXWTBiXAEEniNoMPwAAYcnVjYWdwcGV1AZEaIYn5AZEaIYnrAAAAAQ',
'ext': 'mp4',
'title': 'Spotlight Snap',
'description': 'How he flirt her teacher🤭🤭🤩😍 #kdrama#cdrama #dramaclips #dramaspotlight',
'thumbnail': r're:https://cf-st\.sc-cdn\.net/i/ztfr6xFs0FOcFhwVczWfj\.256\.IRZXSOY',
'duration': 10.91,
'timestamp': 1722720291.307,
'upload_date': '20240803',
'view_count': int,
'repost_count': int,
'uploader': 'ganda0535',
'uploader_url': 'https://www.snapchat.com/add/ganda0535',
'tags': ['#dramaspotlight', '#dramaclips', '#cdrama', '#kdrama'],
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
page_props = self._search_nextjs_data(webpage, video_id)['props']['pageProps']
video_data = traverse_obj(page_props, (
'spotlightFeed', 'spotlightStories',
lambda _, v: v['story']['storyId']['value'] == video_id, 'metadata', any), None)
return {
'id': video_id,
'ext': 'mp4',
**traverse_obj(video_data, ('videoMetadata', {
'title': ('name', {str}),
'description': ('description', {str}),
'timestamp': ('uploadDateMs', {lambda x: float_or_none(x, 1000)}),
'view_count': ('viewCount', {int_or_none}, {lambda x: None if x == -1 else x}),
'repost_count': ('shareCount', {int_or_none}),
'url': ('contentUrl', {url_or_none}),
'width': ('width', {int_or_none}),
'height': ('height', {int_or_none}),
'duration': ('durationMs', {lambda x: float_or_none(x, 1000)}),
'thumbnail': ('thumbnailUrl', {url_or_none}),
'uploader': ('creator', 'personCreator', 'username', {str}),
'uploader_url': ('creator', 'personCreator', 'url', {url_or_none}),
})),
**traverse_obj(video_data, {
'description': ('description', {str}),
'tags': ('hashtags', ..., {str}),
'view_count': ('engagementStats', 'viewCount', {int_or_none}, {lambda x: None if x == -1 else x}),
'repost_count': ('engagementStats', 'shareCount', {int_or_none}),
}),
}