From 14ad06ec6bb79cf83ad7cf04364d6b01433679ff Mon Sep 17 00:00:00 2001
From: Jan Eggers <janeggers@untergeekPro.local>
Date: Sat, 18 Jan 2025 19:13:38 +0100
Subject: [PATCH] Fix bei read_range
---
pyproject.toml | 2 +-
src/aichecker/check_tg.py | 2 +-
tg_hr_check.py | 30 ++++++++++++++++--------------
3 files changed, 18 insertions(+), 16 deletions(-)
diff --git a/pyproject.toml b/pyproject.toml
index 2be555e..6a61e5c 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -10,7 +10,7 @@ authors = [
maintainers = [
{name = "Jan Eggers", email = "jan.eggers@hr.de"},
]
-version = "0.2.4.2" # Neue Versionsnummern für pip-Update
+version = "0.2.4.3" # Neue Versionsnummern für pip-Update
description = "Bluesky- und Telegram-Konten auf KI-Inhalte checken"
requires-python = ">=3.8"
dependencies = [
diff --git a/src/aichecker/check_tg.py b/src/aichecker/check_tg.py
index 8c9e72e..562d30e 100644
--- a/src/aichecker/check_tg.py
+++ b/src/aichecker/check_tg.py
@@ -381,7 +381,7 @@ def tgc_read_range(cname, n1=1, n2=None, save=True, describe = True):
posts.append(p)
if p['nr'] == n2:
return posts
- n = max
+ n = p['nr']
return posts
def tgc_read_number(cname, n = 20, cutoff = None, save=True, describe = True):
diff --git a/tg_hr_check.py b/tg_hr_check.py
index b3f84b9..0ee16b1 100644
--- a/tg_hr_check.py
+++ b/tg_hr_check.py
@@ -61,6 +61,7 @@ if __name__ == "__main__":
channels=['fragunsdochdasoriginal','freiheitffm']
hr_links = []
for c in channels:
+ existing_df = pd.DataFrame()
profile = tgc_profile(c)
if profile is None:
print(f"Kein Konto mit dem Namen {c} gefunden.")
@@ -84,21 +85,22 @@ if __name__ == "__main__":
start_post = max(existing_df['nr'])
print(f"Dieser Kanal wurde schon einmal ausgelesen, zuletzt Post Nr.: {start_post} - seitdem {last_post-start_post} neue Posts")
else:
- start_post = last_post-N+1
+ start_post = last_post-N
print(f"Noch nicht gespeichert. Importiere {N} Posts bis zum letzten: {last_post}.")
# Lies die aktuellsten Posts, sichere und analysiere sie
#
- print("Einlesen {start_post} bis {last_post}...")
- posts = tgc_read_range(c, start_post, last_post, save=False, describe= False)
- # Nach hr-Links suchen
- for post in posts:
- interessant = find_hr_links(post['text'])
- if post['links']:
- interessant.extend(post['links'])
- hr_links.extend(interessant)
- print(f"Potenziell interessant: {interessant}")
- # Posts anhängen an das csv dieses Kanals
- df = pd.DataFrame(posts)
- if ('existing_df' in globals()):
+ if start_post < last_post:
+ print(f"Einlesen {start_post+1} bis {last_post}...")
+ posts = tgc_read_range(c, start_post+1, last_post, save=False, describe= False)
+ # Nach hr-Links suchen
+ for post in posts:
+ interessant = find_hr_links(post['text'])
+ if post['links']:
+ interessant.extend(post['links'])
+ hr_links.extend(interessant)
+ print(f"Potenziell interessant: {interessant}")
+ # Posts anhängen an das csv dieses Kanals
+ df = pd.DataFrame(posts)
df = pd.concat([existing_df, df]).drop_duplicates(subset=['nr']).reset_index(drop=True)
- df.to_csv(f'tg-checks/{c}.csv', index=False) # Save to CSV for example
+ df.to_csv(f'tg-checks/{c}.csv', index=False) # Save to CSV for example
+ print("Ende Gelände.")
--
GitLab