refine table parser (#120)

This commit is contained in:
KevinHuSh
2024-03-12 18:56:04 +08:00
committed by GitHub
parent f1f09df901
commit 0feb085c88
6 changed files with 20 additions and 15 deletions

View File

@ -91,10 +91,10 @@ def dispatch():
tsks.append(task)
elif r["parser_id"] == "table":
rn = HuExcelParser.row_number(r["name"], MINIO.get(r["kb_id"], r["location"]))
for i in range(0, rn, 1000):
for i in range(0, rn, 3000):
task = new_task()
task["from_page"] = i
task["to_page"] = min(i + 1000, rn)
task["to_page"] = min(i + 3000, rn)
tsks.append(task)
else:
tsks.append(new_task())