Floke/Brancheneinstufung2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(competitor-analysis): final migration fixes and documentation updates

Browse Source
This commit is contained in:
Floke
2026-05-15 20:25:47 +00:00
parent 726fcc38ce
commit ec0a977211
2 changed files with 43 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
fotograf-de-scraper/backend/main.py
View File

@@ -550,18 +550,19 @@ def process_reminder_analysis(task_id: str, job_id: str, account_type: str, max_
task_store[task_id] = {"status": "error", "progress": "Keine Daten vorhanden. Bitte erst oben auf 'Daten abgleichen' klicken."}
return
# 1. Get emails that have ALREADY purchased anything (in ANY job we have in DB)
# 1. Get emails that have ALREADY purchased anything (in THIS specific job)
purchased_emails = set()
if exclude_purchased_emails:
from sqlalchemy import or_
# We look globally across the whole job_participants table
# We look ONLY within the CURRENT job to find siblings that were already purchased
purchased_results = db.query(JobParticipant.email_eltern).filter(
JobParticipant.job_id == job_id,
or_(JobParticipant.has_orders == 1, JobParticipant.digital_package_ordered == 1),
JobParticipant.email_eltern != "",
JobParticipant.email_eltern != None
).all()
purchased_emails = {r[0].lower() for r in purchased_results}
logger.info(f"Task {task_id}: Found {len(purchased_emails)} unique emails with existing purchases in DB to exclude.")
logger.info(f"Task {task_id}: Found {len(purchased_emails)} unique emails with existing purchases in THIS job to exclude.")
# 2. Query DB for potential candidates (Logins <= max_logins and No Orders)
candidates = db.query(JobParticipant).filter(

39
patch_filter.py Normal file
View File

@@ -0,0 +1,39 @@
import sys
with open('fotograf-de-scraper/backend/main.py', 'r') as f:
content = f.read()
old_code = """ # 1. Get emails that have ALREADY purchased anything (in ANY job we have in DB)
purchased_emails = set()
if exclude_purchased_emails:
from sqlalchemy import or_
# We look globally across the whole job_participants table
purchased_results = db.query(JobParticipant.email_eltern).filter(
or_(JobParticipant.has_orders == 1, JobParticipant.digital_package_ordered == 1),
JobParticipant.email_eltern != "",
JobParticipant.email_eltern != None
).all()
purchased_emails = {r[0].lower() for r in purchased_results}
logger.info(f"Task {task_id}: Found {len(purchased_emails)} unique emails with existing purchases in DB to exclude.")"""
new_code = """ # 1. Get emails that have ALREADY purchased anything (in THIS specific job)
purchased_emails = set()
if exclude_purchased_emails:
from sqlalchemy import or_
# We look ONLY within the CURRENT job to find siblings that were already purchased
purchased_results = db.query(JobParticipant.email_eltern).filter(
JobParticipant.job_id == job_id,
or_(JobParticipant.has_orders == 1, JobParticipant.digital_package_ordered == 1),
JobParticipant.email_eltern != "",
JobParticipant.email_eltern != None
).all()
purchased_emails = {r[0].lower() for r in purchased_results}
logger.info(f"Task {task_id}: Found {len(purchased_emails)} unique emails with existing purchases in THIS job to exclude.")"""
if old_code in content:
content = content.replace(old_code, new_code)
with open('fotograf-de-scraper/backend/main.py', 'w') as f:
f.write(content)
print("Filter logic patched successfully")
else:
print("Old code not found")