You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
kmftools/bookscraper/scraper/tasks/scraping.py

102 lines
3.5 KiB

# ============================================================
# File: scraper/tasks/scraping.py
# Purpose:
# Scrape ONLY metadata + chapter list.
# Does NOT launch download controller anymore.
# Controller decides when pipelines start.
# ============================================================
from celery_app import celery_app
from logbus.publisher import log
import os
import redis
from scraper.logger_decorators import logcall
from scraper.sites import BookSite
from scraper.book_scraper import BookScraper
from scraper.abort import clear_abort
from scraper.ui_log import reset_ui_logs
from scraper.services.init_service import InitService
print(">>> [IMPORT] scraping.py loaded")
# Redis connection (same DB as Celery broker)
REDIS_URL = os.getenv("REDIS_BROKER", "redis://redis:6379/0")
r = redis.Redis.from_url(REDIS_URL, decode_responses=True)
@celery_app.task(
bind=True,
queue="scraping",
ignore_result=False,
name="scraper.tasks.scraping.start_scrape_book",
)
@logcall
def start_scrape_book(self, url: str):
"""
Scrapes metadata + chapters.
DOES NOT START download / pipeline controller.
The controller_tasks.start_full_scrape() task will call this one.
"""
# ------------------------------------------------------------
# CLEAR UI LOG BUFFER
# ------------------------------------------------------------
reset_ui_logs()
log(f"[SCRAPING] Start scraping for: {url}")
# ------------------------------------------------------------
# SCRAPE (old engine)
# ------------------------------------------------------------
site = BookSite()
scraper = BookScraper(site, url)
result = scraper.execute() # → { title, author, chapters, cover_url, ... }
chapters = result.get("chapters", [])
full_count = len(chapters)
# ------------------------------------------------------------
# Compute unified book_idx
# ------------------------------------------------------------
book_idx = InitService.derive_book_id(url)
result["book_idx"] = book_idx
log(f"[SCRAPING] Assigned book_idx = {book_idx}")
# ------------------------------------------------------------
# DRY RUN TEST LIMIT
# ------------------------------------------------------------
DRY_RUN = os.getenv("DRY_RUN", "0") == "1"
TEST_LIMIT = int(os.getenv("TEST_LIMIT", "5"))
if DRY_RUN:
log(f"[SCRAPING] DRY RUN active → limiting chapters to {TEST_LIMIT}")
result["chapters"] = chapters[:TEST_LIMIT]
# ------------------------------------------------------------
# LOG RESULTS
# ------------------------------------------------------------
log(
f"[SCRAPING] Completed scrape: "
f"{len(result['chapters'])}/{full_count} chapters"
)
# ------------------------------------------------------------
# RESET ABORT + INITIALIZE LEGACY PROGRESS
# ------------------------------------------------------------
clear_abort(book_idx)
r.set(f"progress:{book_idx}:total", len(result["chapters"]))
r.set(f"progress:{book_idx}:done", 0)
r.delete(f"logs:{book_idx}")
r.rpush(f"logs:{book_idx}", f":: SCRAPING STARTED for {url}")
r.rpush(f"logs:{book_idx}", f":: Found {len(result['chapters'])} chapters")
# ------------------------------------------------------------
# IMPORTANT: DO NOT DISPATCH any pipelines here
# Controller will receive scrape_result and continue.
# ------------------------------------------------------------
return result