mirror of
https://github.com/tubearchivist/tubearchivist-frontend.git
synced 2024-11-22 11:50:14 +00:00
refactor and consolidate Reindex class
This commit is contained in:
parent
1f7d6871cf
commit
fda520ad44
@ -10,7 +10,6 @@ import os
|
|||||||
import re
|
import re
|
||||||
import shutil
|
import shutil
|
||||||
import subprocess
|
import subprocess
|
||||||
from datetime import datetime
|
|
||||||
|
|
||||||
import requests
|
import requests
|
||||||
from home.src.download.queue import PendingList
|
from home.src.download.queue import PendingList
|
||||||
@ -319,10 +318,7 @@ def scan_filesystem():
|
|||||||
|
|
||||||
def reindex_old_documents():
|
def reindex_old_documents():
|
||||||
"""daily refresh of old documents"""
|
"""daily refresh of old documents"""
|
||||||
# continue if needed
|
handler = Reindex()
|
||||||
reindex_handler = Reindex()
|
handler.check_outdated()
|
||||||
reindex_handler.check_outdated()
|
handler.reindex()
|
||||||
reindex_handler.reindex()
|
RedisArchivist().set_message("last_reindex", handler.now, expire=False)
|
||||||
# set timestamp
|
|
||||||
now = int(datetime.now().strftime("%s"))
|
|
||||||
RedisArchivist().set_message("last_reindex", now, expire=False)
|
|
||||||
|
@ -4,85 +4,60 @@ functionality:
|
|||||||
- index and update in es
|
- index and update in es
|
||||||
"""
|
"""
|
||||||
|
|
||||||
import json
|
|
||||||
from datetime import datetime
|
from datetime import datetime
|
||||||
from math import ceil
|
from math import ceil
|
||||||
from time import sleep
|
from time import sleep
|
||||||
|
|
||||||
import requests
|
|
||||||
from home.src.download.queue import PendingList
|
from home.src.download.queue import PendingList
|
||||||
from home.src.download.thumbnails import ThumbManager
|
from home.src.download.thumbnails import ThumbManager
|
||||||
|
from home.src.es.connect import ElasticWrap
|
||||||
from home.src.index.channel import YoutubeChannel
|
from home.src.index.channel import YoutubeChannel
|
||||||
from home.src.index.playlist import YoutubePlaylist
|
from home.src.index.playlist import YoutubePlaylist
|
||||||
from home.src.index.video import YoutubeVideo
|
from home.src.index.video import YoutubeVideo
|
||||||
from home.src.ta.config import AppConfig
|
from home.src.ta.config import AppConfig
|
||||||
from home.src.ta.helper import get_total_hits
|
|
||||||
|
|
||||||
|
|
||||||
class Reindex:
|
class Reindex:
|
||||||
"""check for outdated documents and refresh data from youtube"""
|
"""check for outdated documents and refresh data from youtube"""
|
||||||
|
|
||||||
|
MATCH_FIELD = {
|
||||||
|
"ta_video": "active",
|
||||||
|
"ta_channel": "channel_active",
|
||||||
|
"ta_playlist": "playlist_active",
|
||||||
|
}
|
||||||
|
MULTIPLY = 1.2
|
||||||
|
|
||||||
def __init__(self):
|
def __init__(self):
|
||||||
# config
|
# config
|
||||||
config = AppConfig().config
|
self.now = int(datetime.now().strftime("%s"))
|
||||||
self.sleep_interval = config["downloads"]["sleep_interval"]
|
self.config = AppConfig().config
|
||||||
self.es_url = config["application"]["es_url"]
|
self.interval = self.config["scheduler"]["check_reindex_days"]
|
||||||
self.es_auth = config["application"]["es_auth"]
|
|
||||||
self.refresh_interval = config["scheduler"]["check_reindex_days"]
|
|
||||||
self.integrate_ryd = config["downloads"]["integrate_ryd"]
|
|
||||||
# scan
|
# scan
|
||||||
self.all_youtube_ids = False
|
self.all_youtube_ids = False
|
||||||
self.all_channel_ids = False
|
self.all_channel_ids = False
|
||||||
self.all_playlist_ids = False
|
self.all_playlist_ids = False
|
||||||
|
|
||||||
def get_daily(self):
|
def _get_daily(self):
|
||||||
"""get daily refresh values"""
|
"""get daily refresh values"""
|
||||||
total_videos = get_total_hits(
|
total_videos = self._get_total_hits("ta_video")
|
||||||
"ta_video", self.es_url, self.es_auth, "active"
|
video_daily = ceil(total_videos / self.interval * self.MULTIPLY)
|
||||||
)
|
total_channels = self._get_total_hits("ta_channel")
|
||||||
video_daily = ceil(total_videos / self.refresh_interval * 1.2)
|
channel_daily = ceil(total_channels / self.interval * self.MULTIPLY)
|
||||||
total_channels = get_total_hits(
|
total_playlists = self._get_total_hits("ta_playlist")
|
||||||
"ta_channel", self.es_url, self.es_auth, "channel_active"
|
playlist_daily = ceil(total_playlists / self.interval * self.MULTIPLY)
|
||||||
)
|
|
||||||
channel_daily = ceil(total_channels / self.refresh_interval * 1.2)
|
|
||||||
total_playlists = get_total_hits(
|
|
||||||
"ta_playlist", self.es_url, self.es_auth, "playlist_active"
|
|
||||||
)
|
|
||||||
playlist_daily = ceil(total_playlists / self.refresh_interval * 1.2)
|
|
||||||
return (video_daily, channel_daily, playlist_daily)
|
return (video_daily, channel_daily, playlist_daily)
|
||||||
|
|
||||||
def get_outdated_vids(self, size):
|
def _get_total_hits(self, index):
|
||||||
"""get daily videos to refresh"""
|
"""get total hits from index"""
|
||||||
headers = {"Content-type": "application/json"}
|
match_field = self.MATCH_FIELD[index]
|
||||||
now = int(datetime.now().strftime("%s"))
|
path = f"{index}/_search?filter_path=hits.total"
|
||||||
now_lte = now - self.refresh_interval * 24 * 60 * 60
|
data = {"query": {"match": {match_field: True}}}
|
||||||
data = {
|
response, _ = ElasticWrap(path).post(data=data)
|
||||||
"size": size,
|
total_hits = response["hits"]["total"]["value"]
|
||||||
"query": {
|
return total_hits
|
||||||
"bool": {
|
|
||||||
"must": [
|
|
||||||
{"match": {"active": True}},
|
|
||||||
{"range": {"vid_last_refresh": {"lte": now_lte}}},
|
|
||||||
]
|
|
||||||
}
|
|
||||||
},
|
|
||||||
"sort": [{"vid_last_refresh": {"order": "asc"}}],
|
|
||||||
"_source": False,
|
|
||||||
}
|
|
||||||
query_str = json.dumps(data)
|
|
||||||
url = self.es_url + "/ta_video/_search"
|
|
||||||
response = requests.get(
|
|
||||||
url, data=query_str, headers=headers, auth=self.es_auth
|
|
||||||
)
|
|
||||||
if not response.ok:
|
|
||||||
print(response.text)
|
|
||||||
response_dict = json.loads(response.text)
|
|
||||||
all_youtube_ids = [i["_id"] for i in response_dict["hits"]["hits"]]
|
|
||||||
return all_youtube_ids
|
|
||||||
|
|
||||||
def get_unrated_vids(self):
|
def _get_unrated_vids(self):
|
||||||
"""get all videos without rating if ryd integration is enabled"""
|
"""get max 200 videos without rating if ryd integration is enabled"""
|
||||||
headers = {"Content-type": "application/json"}
|
|
||||||
data = {
|
data = {
|
||||||
"size": 200,
|
"size": 200,
|
||||||
"query": {
|
"query": {
|
||||||
@ -91,86 +66,78 @@ class Reindex:
|
|||||||
}
|
}
|
||||||
},
|
},
|
||||||
}
|
}
|
||||||
query_str = json.dumps(data)
|
response, _ = ElasticWrap("ta_video/_search").get(data=data)
|
||||||
url = self.es_url + "/ta_video/_search"
|
|
||||||
response = requests.get(
|
missing_rating = [i["_id"] for i in response["hits"]["hits"]]
|
||||||
url, data=query_str, headers=headers, auth=self.es_auth
|
|
||||||
)
|
|
||||||
if not response.ok:
|
|
||||||
print(response.text)
|
|
||||||
response_dict = json.loads(response.text)
|
|
||||||
missing_rating = [i["_id"] for i in response_dict["hits"]["hits"]]
|
|
||||||
self.all_youtube_ids = self.all_youtube_ids + missing_rating
|
self.all_youtube_ids = self.all_youtube_ids + missing_rating
|
||||||
|
|
||||||
def get_outdated_channels(self, size):
|
def _get_outdated_vids(self, size):
|
||||||
"""get daily channels to refresh"""
|
"""get daily videos to refresh"""
|
||||||
headers = {"Content-type": "application/json"}
|
now_lte = self.now - self.interval * 24 * 60 * 60
|
||||||
now = int(datetime.now().strftime("%s"))
|
must_list = [
|
||||||
now_lte = now - self.refresh_interval * 24 * 60 * 60
|
{"match": {"active": True}},
|
||||||
|
{"range": {"vid_last_refresh": {"lte": now_lte}}},
|
||||||
|
]
|
||||||
data = {
|
data = {
|
||||||
"size": size,
|
"size": size,
|
||||||
"query": {
|
"query": {"bool": {"must": must_list}},
|
||||||
"bool": {
|
"sort": [{"vid_last_refresh": {"order": "asc"}}],
|
||||||
"must": [
|
"_source": False,
|
||||||
{"match": {"channel_active": True}},
|
}
|
||||||
{"range": {"channel_last_refresh": {"lte": now_lte}}},
|
response, _ = ElasticWrap("ta_video/_search").get(data=data)
|
||||||
]
|
|
||||||
}
|
all_youtube_ids = [i["_id"] for i in response["hits"]["hits"]]
|
||||||
},
|
return all_youtube_ids
|
||||||
|
|
||||||
|
def _get_outdated_channels(self, size):
|
||||||
|
"""get daily channels to refresh"""
|
||||||
|
now_lte = self.now - self.interval * 24 * 60 * 60
|
||||||
|
must_list = [
|
||||||
|
{"match": {"channel_active": True}},
|
||||||
|
{"range": {"channel_last_refresh": {"lte": now_lte}}},
|
||||||
|
]
|
||||||
|
data = {
|
||||||
|
"size": size,
|
||||||
|
"query": {"bool": {"must": must_list}},
|
||||||
"sort": [{"channel_last_refresh": {"order": "asc"}}],
|
"sort": [{"channel_last_refresh": {"order": "asc"}}],
|
||||||
"_source": False,
|
"_source": False,
|
||||||
}
|
}
|
||||||
query_str = json.dumps(data)
|
response, _ = ElasticWrap("ta_channel/_search").get(data=data)
|
||||||
url = self.es_url + "/ta_channel/_search"
|
|
||||||
response = requests.get(
|
all_channel_ids = [i["_id"] for i in response["hits"]["hits"]]
|
||||||
url, data=query_str, headers=headers, auth=self.es_auth
|
|
||||||
)
|
|
||||||
if not response.ok:
|
|
||||||
print(response.text)
|
|
||||||
response_dict = json.loads(response.text)
|
|
||||||
all_channel_ids = [i["_id"] for i in response_dict["hits"]["hits"]]
|
|
||||||
return all_channel_ids
|
return all_channel_ids
|
||||||
|
|
||||||
def get_outdated_playlists(self, size):
|
def _get_outdated_playlists(self, size):
|
||||||
"""get daily outdated playlists to refresh"""
|
"""get daily outdated playlists to refresh"""
|
||||||
headers = {"Content-type": "application/json"}
|
now_lte = self.now - self.interval * 24 * 60 * 60
|
||||||
now = int(datetime.now().strftime("%s"))
|
must_list = [
|
||||||
now_lte = now - self.refresh_interval * 24 * 60 * 60
|
{"match": {"playlist_active": True}},
|
||||||
|
{"range": {"playlist_last_refresh": {"lte": now_lte}}},
|
||||||
|
]
|
||||||
data = {
|
data = {
|
||||||
"size": size,
|
"size": size,
|
||||||
"query": {
|
"query": {"bool": {"must": must_list}},
|
||||||
"bool": {
|
|
||||||
"must": [
|
|
||||||
{"match": {"playlist_active": True}},
|
|
||||||
{"range": {"playlist_last_refresh": {"lte": now_lte}}},
|
|
||||||
]
|
|
||||||
}
|
|
||||||
},
|
|
||||||
"sort": [{"playlist_last_refresh": {"order": "asc"}}],
|
"sort": [{"playlist_last_refresh": {"order": "asc"}}],
|
||||||
"_source": False,
|
"_source": False,
|
||||||
}
|
}
|
||||||
query_str = json.dumps(data)
|
response, _ = ElasticWrap("ta_playlist/_search").get(data=data)
|
||||||
url = self.es_url + "/ta_playlist/_search"
|
|
||||||
response = requests.get(
|
all_playlist_ids = [i["_id"] for i in response["hits"]["hits"]]
|
||||||
url, data=query_str, headers=headers, auth=self.es_auth
|
|
||||||
)
|
|
||||||
if not response.ok:
|
|
||||||
print(response.text)
|
|
||||||
response_dict = json.loads(response.text)
|
|
||||||
all_playlist_ids = [i["_id"] for i in response_dict["hits"]["hits"]]
|
|
||||||
return all_playlist_ids
|
return all_playlist_ids
|
||||||
|
|
||||||
def check_outdated(self):
|
def check_outdated(self):
|
||||||
"""add missing vids and channels"""
|
"""add missing vids and channels"""
|
||||||
video_daily, channel_daily, playlist_daily = self.get_daily()
|
video_daily, channel_daily, playlist_daily = self._get_daily()
|
||||||
self.all_youtube_ids = self.get_outdated_vids(video_daily)
|
self.all_youtube_ids = self._get_outdated_vids(video_daily)
|
||||||
self.all_channel_ids = self.get_outdated_channels(channel_daily)
|
self.all_channel_ids = self._get_outdated_channels(channel_daily)
|
||||||
self.all_playlist_ids = self.get_outdated_playlists(playlist_daily)
|
self.all_playlist_ids = self._get_outdated_playlists(playlist_daily)
|
||||||
if self.integrate_ryd:
|
|
||||||
self.get_unrated_vids()
|
integrate_ryd = self.config["downloads"]["integrate_ryd"]
|
||||||
|
if integrate_ryd:
|
||||||
|
self._get_unrated_vids()
|
||||||
|
|
||||||
@staticmethod
|
@staticmethod
|
||||||
def reindex_single_video(youtube_id):
|
def _reindex_single_video(youtube_id):
|
||||||
"""refresh data for single video"""
|
"""refresh data for single video"""
|
||||||
video = YoutubeVideo(youtube_id)
|
video = YoutubeVideo(youtube_id)
|
||||||
|
|
||||||
@ -204,20 +171,21 @@ class Reindex:
|
|||||||
return
|
return
|
||||||
|
|
||||||
@staticmethod
|
@staticmethod
|
||||||
def reindex_single_channel(channel_id):
|
def _reindex_single_channel(channel_id):
|
||||||
"""refresh channel data and sync to videos"""
|
"""refresh channel data and sync to videos"""
|
||||||
channel = YoutubeChannel(channel_id)
|
channel = YoutubeChannel(channel_id)
|
||||||
channel.get_from_es()
|
channel.get_from_es()
|
||||||
subscribed = channel.json_data["channel_subscribed"]
|
subscribed = channel.json_data["channel_subscribed"]
|
||||||
overwrites = channel.json_data["channel_overwrites"]
|
overwrites = channel.json_data.get("channel_overwrites", False)
|
||||||
channel.get_from_youtube()
|
channel.get_from_youtube()
|
||||||
channel.json_data["channel_subscribed"] = subscribed
|
channel.json_data["channel_subscribed"] = subscribed
|
||||||
channel.json_data["channel_overwrites"] = overwrites
|
if overwrites:
|
||||||
|
channel.json_data["channel_overwrites"] = overwrites
|
||||||
channel.upload_to_es()
|
channel.upload_to_es()
|
||||||
channel.sync_to_videos()
|
channel.sync_to_videos()
|
||||||
|
|
||||||
@staticmethod
|
@staticmethod
|
||||||
def reindex_single_playlist(playlist_id, all_indexed_ids):
|
def _reindex_single_playlist(playlist_id, all_indexed_ids):
|
||||||
"""refresh playlist data"""
|
"""refresh playlist data"""
|
||||||
playlist = YoutubePlaylist(playlist_id)
|
playlist = YoutubePlaylist(playlist_id)
|
||||||
playlist.get_from_es()
|
playlist.get_from_es()
|
||||||
@ -234,18 +202,19 @@ class Reindex:
|
|||||||
|
|
||||||
def reindex(self):
|
def reindex(self):
|
||||||
"""reindex what's needed"""
|
"""reindex what's needed"""
|
||||||
|
sleep_interval = self.config["downloads"]["sleep_interval"]
|
||||||
# videos
|
# videos
|
||||||
print(f"reindexing {len(self.all_youtube_ids)} videos")
|
print(f"reindexing {len(self.all_youtube_ids)} videos")
|
||||||
for youtube_id in self.all_youtube_ids:
|
for youtube_id in self.all_youtube_ids:
|
||||||
self.reindex_single_video(youtube_id)
|
self._reindex_single_video(youtube_id)
|
||||||
if self.sleep_interval:
|
if sleep_interval:
|
||||||
sleep(self.sleep_interval)
|
sleep(sleep_interval)
|
||||||
# channels
|
# channels
|
||||||
print(f"reindexing {len(self.all_channel_ids)} channels")
|
print(f"reindexing {len(self.all_channel_ids)} channels")
|
||||||
for channel_id in self.all_channel_ids:
|
for channel_id in self.all_channel_ids:
|
||||||
self.reindex_single_channel(channel_id)
|
self._reindex_single_channel(channel_id)
|
||||||
if self.sleep_interval:
|
if sleep_interval:
|
||||||
sleep(self.sleep_interval)
|
sleep(sleep_interval)
|
||||||
# playlist
|
# playlist
|
||||||
print(f"reindexing {len(self.all_playlist_ids)} playlists")
|
print(f"reindexing {len(self.all_playlist_ids)} playlists")
|
||||||
if self.all_playlist_ids:
|
if self.all_playlist_ids:
|
||||||
@ -253,6 +222,6 @@ class Reindex:
|
|||||||
handler.get_indexed()
|
handler.get_indexed()
|
||||||
all_indexed_ids = [i["youtube_id"] for i in handler.all_videos]
|
all_indexed_ids = [i["youtube_id"] for i in handler.all_videos]
|
||||||
for playlist_id in self.all_playlist_ids:
|
for playlist_id in self.all_playlist_ids:
|
||||||
self.reindex_single_playlist(playlist_id, all_indexed_ids)
|
self._reindex_single_playlist(playlist_id, all_indexed_ids)
|
||||||
if self.sleep_interval:
|
if sleep_interval:
|
||||||
sleep(self.sleep_interval)
|
sleep(sleep_interval)
|
||||||
|
@ -3,31 +3,15 @@ Loose collection of helper functions
|
|||||||
- don't import AppConfig class here to avoid circular imports
|
- don't import AppConfig class here to avoid circular imports
|
||||||
"""
|
"""
|
||||||
|
|
||||||
import json
|
|
||||||
import re
|
import re
|
||||||
import string
|
import string
|
||||||
import subprocess
|
import subprocess
|
||||||
import unicodedata
|
import unicodedata
|
||||||
from urllib.parse import parse_qs, urlparse
|
from urllib.parse import parse_qs, urlparse
|
||||||
|
|
||||||
import requests
|
|
||||||
import yt_dlp
|
import yt_dlp
|
||||||
|
|
||||||
|
|
||||||
def get_total_hits(index, es_url, es_auth, match_field):
|
|
||||||
"""get total hits from index"""
|
|
||||||
headers = {"Content-type": "application/json"}
|
|
||||||
data = {"query": {"match": {match_field: True}}}
|
|
||||||
payload = json.dumps(data)
|
|
||||||
url = f"{es_url}/{index}/_search?filter_path=hits.total"
|
|
||||||
request = requests.post(url, data=payload, headers=headers, auth=es_auth)
|
|
||||||
if not request.ok:
|
|
||||||
print(request.text)
|
|
||||||
total_json = json.loads(request.text)
|
|
||||||
total_hits = total_json["hits"]["total"]["value"]
|
|
||||||
return total_hits
|
|
||||||
|
|
||||||
|
|
||||||
def clean_string(file_name):
|
def clean_string(file_name):
|
||||||
"""clean string to only asci characters"""
|
"""clean string to only asci characters"""
|
||||||
whitelist = "-_.() " + string.ascii_letters + string.digits
|
whitelist = "-_.() " + string.ascii_letters + string.digits
|
||||||
|
Loading…
Reference in New Issue
Block a user