Spaces:
Sleeping
Sleeping
Update app/fetcher/youtube_client.py
Browse files- app/fetcher/youtube_client.py +62 -62
app/fetcher/youtube_client.py
CHANGED
|
@@ -1,62 +1,62 @@
|
|
| 1 |
-
"""
|
| 2 |
-
ResearchRadar — YouTube Video Fetcher (Robust).
|
| 3 |
-
"""
|
| 4 |
-
|
| 5 |
-
from __future__ import annotations
|
| 6 |
-
|
| 7 |
-
import logging
|
| 8 |
-
import xml.etree.ElementTree as ET
|
| 9 |
-
from typing import Dict, List
|
| 10 |
-
|
| 11 |
-
import requests
|
| 12 |
-
from app.fetcher.http_session import RetrySession
|
| 13 |
-
|
| 14 |
-
logger = logging.getLogger(__name__)
|
| 15 |
-
|
| 16 |
-
_AI_CHANNEL_IDS = [
|
| 17 |
-
'UCghJTNTO9kcDeUFXMuSDGLQ', # Two Minute Papers
|
| 18 |
-
'UCLKPca3kwwd-B59HNr-_lvA', # AI Explained
|
| 19 |
-
'UCZHmQk67mSJgfCCTn7xBfew', # Yannic Kilcher
|
| 20 |
-
'UCYUq87t77YNTG5m256fOXeQ',
|
| 21 |
-
'UCgBncpylJ1kiVaPyP-PZauQ',
|
| 22 |
-
'UC6MhHkSosYXAD-LTXBWyLMg',
|
| 23 |
-
'UCJgIbYl6C5no72a0NUAPcTA',
|
| 24 |
-
'UCNIkB2IeJ-6AmZv7bQ1oBYg',
|
| 25 |
-
# Sentdex
|
| 26 |
-
]
|
| 27 |
-
|
| 28 |
-
def fetch_latest_videos(limit_per_channel: int = 1) -> List[Dict[str, str]]:
|
| 29 |
-
"""Pulls the most recent videos from our list of AI YouTube channels."""
|
| 30 |
-
session = RetrySession()
|
| 31 |
-
videos = []
|
| 32 |
-
|
| 33 |
-
for cid in _AI_CHANNEL_IDS:
|
| 34 |
-
url = f"https://www.youtube.com/feeds/videos.xml?channel_id={cid}"
|
| 35 |
-
try:
|
| 36 |
-
resp = session.get(url)
|
| 37 |
-
if resp.status_code == 200:
|
| 38 |
-
root = ET.fromstring(resp.text)
|
| 39 |
-
ns = {'a': 'http://www.w3.org/2005/Atom'}
|
| 40 |
-
|
| 41 |
-
entries = root.findall('a:entry', ns)
|
| 42 |
-
logger.info(f"YouTube: Found {len(entries)} entries for channel {cid}")
|
| 43 |
-
|
| 44 |
-
for entry in entries[:limit_per_channel]:
|
| 45 |
-
title_elem = entry.find('a:title', ns)
|
| 46 |
-
title = title_elem.text if title_elem is not None else "Unknown Title"
|
| 47 |
-
|
| 48 |
-
# Find the link with rel="alternate"
|
| 49 |
-
link = ""
|
| 50 |
-
for link_elem in entry.findall('a:link', ns):
|
| 51 |
-
if link_elem.attrib.get('rel') == 'alternate':
|
| 52 |
-
link = link_elem.attrib.get('href', '')
|
| 53 |
-
break
|
| 54 |
-
|
| 55 |
-
if title and link:
|
| 56 |
-
videos.append({'title': title, 'url': link})
|
| 57 |
-
else:
|
| 58 |
-
logger.warning(f"YouTube RSS status {resp.status_code} for {cid}")
|
| 59 |
-
except Exception as e:
|
| 60 |
-
logger.error(f"Error fetching YouTube feed for channel {cid}: {e}")
|
| 61 |
-
|
| 62 |
-
return videos
|
|
|
|
| 1 |
+
"""
|
| 2 |
+
ResearchRadar — YouTube Video Fetcher (Robust).
|
| 3 |
+
"""
|
| 4 |
+
|
| 5 |
+
from __future__ import annotations
|
| 6 |
+
|
| 7 |
+
import logging
|
| 8 |
+
import xml.etree.ElementTree as ET
|
| 9 |
+
from typing import Dict, List
|
| 10 |
+
|
| 11 |
+
import requests
|
| 12 |
+
from app.fetcher.http_session import RetrySession
|
| 13 |
+
|
| 14 |
+
logger = logging.getLogger(__name__)
|
| 15 |
+
|
| 16 |
+
_AI_CHANNEL_IDS = [
|
| 17 |
+
'UCghJTNTO9kcDeUFXMuSDGLQ', # Two Minute Papers
|
| 18 |
+
'UCLKPca3kwwd-B59HNr-_lvA', # AI Explained
|
| 19 |
+
'UCZHmQk67mSJgfCCTn7xBfew', # Yannic Kilcher
|
| 20 |
+
'UCYUq87t77YNTG5m256fOXeQ',
|
| 21 |
+
'UCgBncpylJ1kiVaPyP-PZauQ',
|
| 22 |
+
'UC6MhHkSosYXAD-LTXBWyLMg',
|
| 23 |
+
'UCJgIbYl6C5no72a0NUAPcTA',
|
| 24 |
+
'UCNIkB2IeJ-6AmZv7bQ1oBYg',
|
| 25 |
+
# Sentdex
|
| 26 |
+
]
|
| 27 |
+
|
| 28 |
+
def fetch_latest_videos(limit_per_channel: int = 1) -> List[Dict[str, str]]:
|
| 29 |
+
"""Pulls the most recent videos from our list of AI YouTube channels."""
|
| 30 |
+
session = RetrySession()
|
| 31 |
+
videos = []
|
| 32 |
+
|
| 33 |
+
for cid in _AI_CHANNEL_IDS:
|
| 34 |
+
url = f"https://www.youtube.com/feeds/videos.xml?channel_id={cid}"
|
| 35 |
+
try:
|
| 36 |
+
resp = session.get(url)
|
| 37 |
+
if resp.status_code == 200:
|
| 38 |
+
root = ET.fromstring(resp.text)
|
| 39 |
+
ns = {'a': 'http://www.w3.org/2005/Atom'}
|
| 40 |
+
|
| 41 |
+
entries = root.findall('a:entry', ns)
|
| 42 |
+
logger.info(f"YouTube: Found {len(entries)} entries for channel {cid}")
|
| 43 |
+
|
| 44 |
+
for entry in entries[:limit_per_channel]:
|
| 45 |
+
title_elem = entry.find('a:title', ns)
|
| 46 |
+
title = title_elem.text if title_elem is not None else "Unknown Title"
|
| 47 |
+
|
| 48 |
+
# Find the link with rel="alternate"
|
| 49 |
+
link = ""
|
| 50 |
+
for link_elem in entry.findall('a:link', ns):
|
| 51 |
+
if link_elem.attrib.get('rel') == 'alternate':
|
| 52 |
+
link = link_elem.attrib.get('href', '')
|
| 53 |
+
break
|
| 54 |
+
|
| 55 |
+
if title and link:
|
| 56 |
+
videos.append({'title': title, 'url': link})
|
| 57 |
+
else:
|
| 58 |
+
logger.warning(f"YouTube RSS status {resp.status_code} for {cid}")
|
| 59 |
+
except Exception as e:
|
| 60 |
+
logger.error(f"Error fetching YouTube feed for channel {cid}: {e}")
|
| 61 |
+
|
| 62 |
+
return videos
|