epimetheus: direct tweet lookup via /tweets?tweet_ids= endpoint
Primary path: GET /twitter/tweets?tweet_ids={id} — works for any tweet,
any age, returns full content. Replaces the fragile from:username search
pagination fallback.
Fallback: article endpoint for X long-form articles.
Last resort: placeholder with [Could not fetch] message.
Pentagon-Agent: Epimetheus <3D35839A-7722-4740-B93D-51157F7D5E70>
This commit is contained in:
parent
8f4e583c76
commit
7360f6b22e
1 changed files with 29 additions and 36 deletions
|
|
@ -179,7 +179,34 @@ async def fetch_tweet_by_url(url: str) -> dict | None:
|
|||
|
||||
try:
|
||||
async with aiohttp.ClientSession() as session:
|
||||
# First try article endpoint
|
||||
# Primary: direct tweet lookup by ID (works for any tweet, any age)
|
||||
async with session.get(
|
||||
"https://api.twitterapi.io/twitter/tweets",
|
||||
params={"tweet_ids": tweet_id},
|
||||
headers={"X-API-Key": key},
|
||||
timeout=aiohttp.ClientTimeout(total=10),
|
||||
) as resp:
|
||||
if resp.status == 200:
|
||||
data = await resp.json()
|
||||
tweets = data.get("tweets", [])
|
||||
if tweets:
|
||||
tweet = tweets[0]
|
||||
author_data = tweet.get("author", {})
|
||||
return {
|
||||
"text": tweet.get("text", ""),
|
||||
"url": url,
|
||||
"author": author_data.get("userName", username),
|
||||
"author_name": author_data.get("name", ""),
|
||||
"author_followers": author_data.get("followers", 0),
|
||||
"engagement": (tweet.get("likeCount", 0) or 0) + (tweet.get("retweetCount", 0) or 0),
|
||||
"likes": tweet.get("likeCount", 0),
|
||||
"retweets": tweet.get("retweetCount", 0),
|
||||
"views": tweet.get("viewCount", 0),
|
||||
"tweet_date": tweet.get("createdAt", ""),
|
||||
"is_article": False,
|
||||
}
|
||||
|
||||
# Fallback: try article endpoint (for X long-form articles)
|
||||
async with session.get(
|
||||
"https://api.twitterapi.io/twitter/article",
|
||||
params={"tweet_id": tweet_id},
|
||||
|
|
@ -202,41 +229,7 @@ async def fetch_tweet_by_url(url: str) -> dict | None:
|
|||
"title": article.get("title", ""),
|
||||
}
|
||||
|
||||
# Fallback: search from:username and match by ID
|
||||
# NOTE: fallback only finds recent tweets (~7 days). Older tweets fail. (Ganymede)
|
||||
# Try with cursor pagination to search deeper
|
||||
cursor = ""
|
||||
for page in range(3): # Up to 3 pages
|
||||
params = {"query": f"from:{username}", "queryType": "Latest"}
|
||||
if cursor:
|
||||
params["cursor"] = cursor
|
||||
async with session.get(
|
||||
API_URL,
|
||||
params=params,
|
||||
headers={"X-API-Key": key},
|
||||
timeout=aiohttp.ClientTimeout(total=10),
|
||||
) as resp:
|
||||
if resp.status >= 400:
|
||||
break
|
||||
data = await resp.json()
|
||||
for tweet in data.get("tweets", []):
|
||||
if str(tweet.get("id")) == tweet_id:
|
||||
author = tweet.get("author", {})
|
||||
return {
|
||||
"text": tweet.get("text", ""),
|
||||
"url": url,
|
||||
"author": author.get("userName", username),
|
||||
"author_name": author.get("name", ""),
|
||||
"author_followers": author.get("followers", 0),
|
||||
"engagement": (tweet.get("likeCount", 0) or 0) + (tweet.get("retweetCount", 0) or 0),
|
||||
"tweet_date": tweet.get("createdAt", ""),
|
||||
"is_article": False,
|
||||
}
|
||||
cursor = data.get("next_cursor", "")
|
||||
if not cursor:
|
||||
break
|
||||
|
||||
# If still not found, return placeholder (Ganymede: surface failure)
|
||||
# Both failed — return placeholder (Ganymede: surface failure)
|
||||
return {
|
||||
"text": f"[Could not fetch tweet content from @{username}]",
|
||||
"url": url,
|
||||
|
|
|
|||
Loading…
Reference in a new issue