tubearchivist/tubearchivist-frontend
1
0
Fork 0
mirror of https://github.com/tubearchivist/tubearchivist-frontend.git synced 2024-11-22 20:00:15 +00:00
Code Issues Projects Releases Wiki Activity

use new IndexPaginate class for get_channels and get_playlists

Browse Source
This commit is contained in:
simon 2021-11-18 14:48:31 +07:00
parent f371a03cc7
commit 8b69be645c
No known key found for this signature in database
GPG Key ID: 2C15AA5E89985DD4
1 changed files with 20 additions and 94 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

114
tubearchivist/home/src/download.py
View File

@ -265,56 +265,19 @@ class ChannelSubscription:
self.es_auth = config["application"]["es_auth"] self.es_auth = config["application"]["es_auth"]
self.channel_size = config["subscriptions"]["channel_size"] self.channel_size = config["subscriptions"]["channel_size"]
def get_channels(self, subscribed_only=True): @staticmethod
def get_channels(subscribed_only=True):
"""get a list of all channels subscribed to""" """get a list of all channels subscribed to"""
headers = {"Content-type": "application/json"} data = {
# get PIT ID "sort": [{"channel_name.keyword": {"order": "asc"}}],
url = self.es_url + "/ta_channel/_pit?keep_alive=1m" }
response = requests.post(url, auth=self.es_auth)
json_data = json.loads(response.text)
pit_id = json_data["id"]
# query
if subscribed_only: if subscribed_only:
data = { data["query"] = {"term": {"channel_subscribed": {"value": True}}}
"query": {"term": {"channel_subscribed": {"value": True}}},
"size": 50,
"pit": {"id": pit_id, "keep_alive": "1m"},
"sort": [{"channel_name.keyword": {"order": "asc"}}],
}
else: else:
data = { data["query"] = {"match_all": {}}
"query": {"match_all": {}},
"size": 50, all_channels = IndexPaginate("ta_channel", data).get_results()
"pit": {"id": pit_id, "keep_alive": "1m"},
"sort": [{"channel_name.keyword": {"order": "asc"}}],
}
query_str = json.dumps(data)
url = self.es_url + "/_search"
all_channels = []
while True:
response = requests.get(
url, data=query_str, headers=headers, auth=self.es_auth
)
json_data = json.loads(response.text)
all_hits = json_data["hits"]["hits"]
if all_hits:
for hit in all_hits:
source = hit["_source"]
search_after = hit["sort"]
all_channels.append(source)
# update search_after with last hit data
data["search_after"] = search_after
query_str = json.dumps(data)
else:
break
# clean up PIT
query_str = json.dumps({"id": pit_id})
requests.delete(
self.es_url + "/_pit",
data=query_str,
headers=headers,
auth=self.es_auth,
)
return all_channels return all_channels
def get_last_youtube_videos(self, channel_id, limit=True): def get_last_youtube_videos(self, channel_id, limit=True):
@ -400,56 +363,19 @@ class PlaylistSubscription:
self.es_auth = config["application"]["es_auth"] self.es_auth = config["application"]["es_auth"]
self.channel_size = config["subscriptions"]["channel_size"] self.channel_size = config["subscriptions"]["channel_size"]
def get_playlists(self, subscribed_only=True): @staticmethod
def get_playlists(subscribed_only=True):
"""get a list of all playlists""" """get a list of all playlists"""
headers = {"Content-type": "application/json"} data = {
# get PIT ID "sort": [{"playlist_channel.keyword": {"order": "desc"}}],
url = self.es_url + "/ta_playlist/_pit?keep_alive=1m" }
response = requests.post(url, auth=self.es_auth)
json_data = json.loads(response.text)
pit_id = json_data["id"]
# query
if subscribed_only: if subscribed_only:
data = { data["query"] = {"term": {"playlist_subscribed": {"value": True}}}
"query": {"term": {"playlist_subscribed": {"value": True}}},
"size": 50,
"pit": {"id": pit_id, "keep_alive": "1m"},
"sort": [{"playlist_channel.keyword": {"order": "desc"}}],
}
else: else:
data = { data["query"] = {"match_all": {}}
"query": {"match_all": {}},
"size": 50, all_playlists = IndexPaginate("ta_playlist", data).get_results()
"pit": {"id": pit_id, "keep_alive": "1m"},
"sort": [{"playlist_channel.keyword": {"order": "desc"}}],
}
query_str = json.dumps(data)
url = self.es_url + "/_search"
all_playlists = []
while True:
response = requests.get(
url, data=query_str, headers=headers, auth=self.es_auth
)
json_data = json.loads(response.text)
all_hits = json_data["hits"]["hits"]
if all_hits:
for hit in all_hits:
source = hit["_source"]
search_after = hit["sort"]
all_playlists.append(source)
# update search_after with last hit data
data["search_after"] = search_after
query_str = json.dumps(data)
else:
break
# clean up PIT
query_str = json.dumps({"id": pit_id})
requests.delete(
self.es_url + "/_pit",
data=query_str,
headers=headers,
auth=self.es_auth,
)
return all_playlists return all_playlists