Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2025-02-18 18:17:55 +01:00
Code Issues Releases Wiki Activity

[picta] Update use api v2

Browse Source
This commit is contained in:
oleksis 2020-05-25 02:42:40 -04:00
parent 41c6135520
commit 44aa875818
1 changed files with 105 additions and 93 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

198
youtube_dl/extractor/picta.py
View File

@ -1,132 +1,144 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
from ..compat import compat_str from ..compat import compat_str
from ..utils import ( from ..utils import int_or_none, unified_timestamp, try_get, ExtractorError
int_or_none,
unified_timestamp,
try_get,
base_url,
ExtractorError
)
from .common import InfoExtractor from .common import InfoExtractor
class PictaBaseIE(InfoExtractor): class PictaBaseIE(InfoExtractor):
API_BASE_URL = 'https://api.picta.cu/api/v1/' API_BASE_URL = "https://api.picta.cu/api/v2/"
def _extract_video(self, video, video_id=None, require_title=True): @staticmethod
title = video['results'][0]['nombre'] if require_title else video.get('results')[0].get('nombre') def _extract_video(video, video_id=None, require_title=True):
description = try_get(video, lambda x: x['results'][0]['descripcion'], compat_str) title = (
uploader = try_get(video, lambda x: x['results'][0]['usuario'], compat_str) video["results"][0]["nombre"]
add_date = try_get(video, lambda x: x['results'][0]['fecha_creacion']) if require_title
else video.get("results")[0].get("nombre")
)
description = try_get(
video, lambda x: x["results"][0]["descripcion"], compat_str
)
uploader = try_get(
video, lambda x: x["results"][0]["usuario"]["username"], compat_str
)
add_date = try_get(video, lambda x: x["results"][0]["fecha_creacion"])
timestamp = int_or_none(unified_timestamp(add_date)) timestamp = int_or_none(unified_timestamp(add_date))
thumbnail = try_get(video, lambda x: x['results'][0]['url_imagen']) thumbnail = try_get(video, lambda x: x["results"][0]["url_imagen"])
manifest_url = try_get(video, lambda x: x['results'][0]['url_manifiesto']) manifest_url = try_get(video, lambda x: x["results"][0]["url_manifiesto"])
category = try_get(video, lambda x: x['results'][0]['canal'], compat_str) category = try_get(
video, lambda x: x["results"][0]["canal"]["nombre"], compat_str
)
return { return {
'id': try_get(video, lambda x: x['results'][0]['id'], compat_str) or video_id, "id": try_get(video, lambda x: x["results"][0]["id"], compat_str)
'title': title, or video_id,
'description': description, "title": title,
'thumbnail': thumbnail, "description": description,
'uploader': uploader, "thumbnail": thumbnail,
'timestamp': timestamp, "uploader": uploader,
'category': [category] if category else None, "timestamp": timestamp,
'manifest_url': manifest_url, "category": [category] if category else None,
"manifest_url": manifest_url,
} }
class PictaIE(PictaBaseIE): class PictaIE(PictaBaseIE):
IE_NAME = 'picta' IE_NAME = "picta"
IE_DESC = 'Picta videos' IE_DESC = "Picta videos"
_VALID_URL = r'https?://(?:www\.)?picta\.cu/(?:medias|embed)/(?:\?v=)?(?P<id>[\da-z-]+)' _VALID_URL = (
_formats = { r"https?://(?:www\.)?picta\.cu/(?:medias|embed)/(?:\?v=)?(?P<id>[\da-z-]+)"
# Dash webm )
'0': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
'1': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
'2': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
'3': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
'4': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
# Dash webm audio with opus inside _TESTS = [
'5': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 128}, {
'6': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 134}, "url": "https://www.picta.cu/medias/orishas-everyday-2019-01-16-16-36-42-443003",
"file": "Orishas - Everyday-orishas-everyday-2019-01-16-16-36-42-443003.webm",
} "md5": "7ffdeb0043500c4bb660c04e74e90f7a",
"info_dict": {
_TESTS = [{ "id": "orishas-everyday-2019-01-16-16-36-42-443003",
'url': 'https://www.picta.cu/medias/orishas-everyday-2019-01-16-16-36-42-443003', "ext": "webm",
'file': 'Orishas - Everyday-orishas-everyday-2019-01-16-16-36-42-443003.webm', "title": "Orishas - Everyday",
'md5': '7ffdeb0043500c4bb660c04e74e90f7a', "thumbnail": r"re:^https?://.*imagen/img.*\.png$",
'info_dict': { "upload_date": "20190116",
'id': 'orishas-everyday-2019-01-16-16-36-42-443003', "description": "Orishas - Everyday (Video Oficial)",
'ext': 'webm', "uploader": "admin",
'title': 'Orishas - Everyday', "timestamp": 1547656602,
'thumbnail': r're:^https?://.*imagen/img.*\.png$', },
'upload_date': '20190116', "params": {"format": "4",},
'description': 'Orishas - Everyday (Video Oficial)',
'uploader': 'admin',
'timestamp': 1547656602,
}, },
'params': { {
'format': '4', "url": "https://www.picta.cu/medias/palmiche-galeno-tercer-lugar-torneo-virtual-robotica-2020-05-21-16-15-31-431895",
"file": "Palmiche Galeno tercer lugar en torneo virtual de robótica-palmiche-galeno-tercer-lugar-torneo-virtual-robotica-2020-05-21-16-15-31-431895.mp4",
"md5": "6031b7a3add2eade9c5bef7ecf5d4b02",
"info_dict": {
"id": "palmiche-galeno-tercer-lugar-torneo-virtual-robotica-2020-05-21-16-15-31-431895",
"ext": "mp4",
"title": "Palmiche Galeno tercer lugar en torneo virtual de robótica",
"thumbnail": r"re:^https?://.*imagen/img.*\.jpeg$",
"upload_date": "20200521",
"description": "En esta emisión:\r\n"
"Iniciará en La Habana nuevo método para medir el consumo "
"eléctrico | https://bit.ly/jtlecturacee\r\n"
"GICAcovid: nueva aplicación web para los centros de "
"aislamiento | https://bit.ly/jtgicacovid\r\n"
"Obtuvo Palmiche tercer lugar en la primera competencia "
"virtual de robótica | https://bit.ly/jtpalmichegaleno\r\n"
"\r\n"
"Síguenos en:\r\n"
"Facebook: http://www.facebook.com/JuventudTecnicaCuba\r\n"
"Twitter e Instagram: @juventudtecnica\r\n"
"Telegram: http://t.me/juventudtecnica",
"uploader": "ernestoguerra21",
"timestamp": 1590077731,
},
}, },
}, { {"url": "https://www.picta.cu/embed/?v=818", "only_matching": True,},
'url': 'https://www.picta.cu/embed/?v=818', ]
'only_matching': True,
}]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
if base_url(url).find('medias') != -1: json_url = (
json_url = self.API_BASE_URL + 'publicacion/?format=json&slug_url=%s&tipo=publicacion' % video_id self.API_BASE_URL + "publicacion/?format=json&slug_url_raw=%s" % video_id
else: )
json_url = self.API_BASE_URL + 'publicacion/?format=json&id_publicacion=%s&tipo=publicacion' % video_id video = self._download_json(json_url, video_id, "Downloading video JSON")
video = self._download_json(json_url, video_id, 'Downloading video JSON')
info = self._extract_video(video, video_id) info = self._extract_video(video, video_id)
formats = [] formats = []
# MPD manifest # MPD manifest
if info.get('manifest_url'): if info.get("manifest_url"):
formats.extend(self._extract_mpd_formats(info.get('manifest_url'), video_id, formats_dict=self._formats)) formats.extend(
# Fix some Picta DASH video vp09.00.[dd].08 for 'vcodec': 'vp9', 'acodec':'none' self._extract_mpd_formats(info.get("manifest_url"), video_id)
for f in formats: )
if f.get('acodec') is None and f.get('vcodec') == 'none':
f.update({'vcodec': 'vp9'})
f.update({'acodec': 'none'})
if not formats: if not formats:
raise ExtractorError('Cannot find video formats') raise ExtractorError("Cannot find video formats")
self._sort_formats(formats) self._sort_formats(formats)
info['formats'] = formats info["formats"] = formats
return info return info
class PictaEmbedIE(InfoExtractor): class PictaEmbedIE(InfoExtractor):
IE_NAME = 'picta:embed' IE_NAME = "picta:embed"
IE_DESC = 'Picta embedded videos' IE_DESC = "Picta embedded videos"
_VALID_URL = r'https?://www\.picta\.cu/embed/\?v=(?P<id>[0-9]+)' _VALID_URL = r"https?://www\.picta\.cu/embed/(?:\?v=)?(?P<id>[0-9]+)"
_TEST = { _TEST = {
'url': 'https://www.picta.cu/embed/?v=818', "url": "https://www.picta.cu/embed/?v=818",
'file': 'Orishas - Everyday-orishas-everyday-2019-01-16-16-36-42-443003.webm', "file": "Orishas - Everyday-orishas-everyday-2019-01-16-16-36-42-443003.webm",
'md5': '7ffdeb0043500c4bb660c04e74e90f7a', "md5": "7ffdeb0043500c4bb660c04e74e90f7a",
'info_dict': { "info_dict": {
'id': 'orishas-everyday-2019-01-16-16-36-42-443003', "id": "orishas-everyday-2019-01-16-16-36-42-443003",
'ext': 'webm', "ext": "webm",
'title': 'Orishas - Everyday', "title": "Orishas - Everyday",
'thumbnail': r're:^https?://.*imagen/img.*\.png$', "thumbnail": r"re:^https?://.*imagen/img.*\.png$",
'upload_date': '20190116', "upload_date": "20190116",
'description': 'Orishas - Everyday (Video Oficial)', "description": "Orishas - Everyday (Video Oficial)",
'uploader': 'admin', "uploader": "admin",
'timestamp': 1547656602, "timestamp": 1547656602,
},
'params': {
'format': '4',
}, },
"params": {"format": "4",},
} }
def _real_extract(self, url): def _real_extract(self, url):