Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-22 16:44:32 +01:00
Code Issues Releases Wiki Activity

[bannedvideo] Coding conventions

Browse Source
This commit is contained in:
smege1001 2020-04-03 02:31:03 +01:00
parent 53f669364f
commit b662e68bec
1 changed files with 64 additions and 49 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

113
youtube_dl/extractor/bannedvideo.py
View File

@ -1,10 +1,18 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import json import json
from datetime import datetime
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import (
try_get,
int_or_none,
url_or_none,
float_or_none,
unified_timestamp,
unified_strdate,
)
class BannedVideoIE(InfoExtractor): class BannedVideoIE(InfoExtractor):
_GRAPHQL_API = 'https://api.infowarsmedia.com/graphql' _GRAPHQL_API = 'https://api.infowarsmedia.com/graphql'
@ -122,48 +130,50 @@ fragment VideoComment on Comment {
'thumbnail': r're:^https?://(?:www\.)?assets\.infowarsmedia.com/images/', 'thumbnail': r're:^https?://(?:www\.)?assets\.infowarsmedia.com/images/',
'description': 'The Chinese Communist Party Official Spokesperson At the Ministry of Truth Released Their Statement Exclusively To Alex Jones and Infowars.com', 'description': 'The Chinese Communist Party Official Spokesperson At the Ministry of Truth Released Their Statement Exclusively To Alex Jones and Infowars.com',
'upload_date': '20200324', 'upload_date': '20200324',
'timestamp': 1585084295.064, 'timestamp': 1585087895,
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
video_info = self._download_json( video_info = try_get(
self._GRAPHQL_API, self._download_json(
video_id, self._GRAPHQL_API,
headers=self._GRAPHQL_HEADERS, video_id,
data=json.dumps({ headers=self._GRAPHQL_HEADERS,
'variables': { data=json.dumps({
'id': video_id 'variables': {
}, 'id': video_id
'operationName': 'GetVideo', },
'query': self._GRAPHQL_GETVIDEO_QUERY 'operationName': 'GetVideo',
}).encode('utf8'), 'query': self._GRAPHQL_GETVIDEO_QUERY
).get('data').get('getVideo') }).encode('utf8')),
video_comments = self._download_json( lambda x: x['data']['getVideo'])
self._GRAPHQL_API, video_comments = try_get(
video_id, self._download_json(
headers=self._GRAPHQL_HEADERS, self._GRAPHQL_API,
data=json.dumps({ video_id,
'variables': { headers=self._GRAPHQL_HEADERS,
'id': video_id data=json.dumps({
}, 'variables': {
'operationName': 'GetVideoComments', 'id': video_id
'query': self._GRAPHQL_GETCOMMENTS_QUERY },
}).encode('utf8'), 'operationName': 'GetVideoComments',
).get('data').get('getVideoComments') 'query': self._GRAPHQL_GETCOMMENTS_QUERY
upload_date = datetime.fromisoformat(video_info.get('createdAt')[:-1]) }).encode('utf8')),
lambda x: x['data']['getVideoComments'])
upload_date = video_info.get('createdAt')
metadata = {} metadata = {}
metadata['id'] = video_id metadata['id'] = video_id
metadata['title'] = video_info.get('title')[:-1] metadata['title'] = video_info.get('title')[:-1]
metadata['description'] = video_info.get('summary') metadata['description'] = video_info.get('summary')
metadata['channel'] = video_info.get('channel').get('title') metadata['channel'] = video_info.get('channel').get('title')
metadata['channel_id'] = video_info.get('channel').get('_id') metadata['channel_id'] = video_info.get('channel').get('_id')
metadata['view_count'] = video_info.get('playCount') metadata['view_count'] = int_or_none(video_info.get('playCount'))
metadata['thumbnail'] = video_info.get('largeImage') metadata['thumbnail'] = url_or_none(video_info.get('largeImage'))
metadata['duration'] = video_info.get('videoDuration') metadata['duration'] = float_or_none(video_info.get('videoDuration'), scale=1000)
metadata['upload_date'] = upload_date.strftime('%Y%m%d') metadata['upload_date'] = unified_strdate(upload_date)
metadata['timestamp'] = upload_date.timestamp() metadata['timestamp'] = unified_timestamp(upload_date)
tags = [] tags = []
for tag in video_info.get('tags'): for tag in video_info.get('tags'):
@ -175,7 +185,13 @@ fragment VideoComment on Comment {
if is_live: if is_live:
formats = [] formats = []
formats.extend(self._extract_m3u8_formats(video_info.get('streamUrl'), video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls', live=True)) formats.extend(self._extract_m3u8_formats(
video_info.get('streamUrl'),
video_id,
'mp4',
entry_protocol='m3u8_native',
m3u8_id='hls',
live=True))
metadata['formats'] = formats metadata['formats'] = formats
else: else:
metadata['url'] = video_info.get('directUrl') metadata['url'] = video_info.get('directUrl')
@ -184,36 +200,35 @@ fragment VideoComment on Comment {
comments = [] comments = []
for comment in video_comments: for comment in video_comments:
comment_date = datetime.fromisoformat(comment.get('createdAt')[:-1])
comments.append({ comments.append({
'id': comment.get('_id'), 'id': comment.get('_id'),
'text': comment.get('content'), 'text': comment.get('content'),
'author': comment.get('user').get('username'), 'author': comment.get('user').get('username'),
'author_id': comment.get('user').get('_id'), 'author_id': comment.get('user').get('_id'),
'timestamp': comment_date.timestamp(), 'timestamp': unified_timestamp(comment.get('createdAt')),
'parent': 'root' 'parent': 'root'
}) })
if comment.get('replyCount') > 0: if comment.get('replyCount') > 0:
replies = self._download_json( replies = try_get(
self._GRAPHQL_API, self._download_json(
video_id, self._GRAPHQL_API,
headers=self._GRAPHQL_HEADERS, video_id,
data=json.dumps({ headers=self._GRAPHQL_HEADERS,
'variables': { data=json.dumps({
'id': comment.get('_id') 'variables': {
}, 'id': comment.get('_id')
'operationName': 'GetCommentReplies', },
'query': self._GRAPHQL_GETCOMMENTSREPLIES_QUERY 'operationName': 'GetCommentReplies',
}).encode('utf8'), 'query': self._GRAPHQL_GETCOMMENTSREPLIES_QUERY
).get('data').get('getCommentReplies') }).encode('utf8')),
lambda x: x['data']['getCommentReplies'])
for reply in replies: for reply in replies:
reply_date = datetime.fromisoformat(reply.get('createdAt')[:-1])
comments.append({ comments.append({
'id': reply.get('_id'), 'id': reply.get('_id'),
'text': reply.get('content'), 'text': reply.get('content'),
'author': reply.get('user').get('username'), 'author': reply.get('user').get('username'),
'author_id': reply.get('user').get('_id'), 'author_id': reply.get('user').get('_id'),
'timestamp': reply_date.timestamp(), 'timestamp': unified_timestamp(reply.get('createdAt')),
'parent': comment.get('_id') 'parent': comment.get('_id')
}) })
metadata["comments"] = comments metadata["comments"] = comments