From 488fbf62969df70d90969e2d53b2cbdab5c0ef4d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=D0=9F=D0=B0=D0=B2=D0=BB=D0=BE?=
<96915401+Rimus0cod@users.noreply.github.com>
Date: Mon, 5 Oct 2026 15:07:44 +0300
Subject: [PATCH 01/13] refactor: add scraper package
---
app/scraper/__init__.py | 3 +++
1 file changed, 3 insertions(+)
create mode 100644 app/scraper/__init__.py
diff --git a/app/scraper/__init__.py b/app/scraper/__init__.py
new file mode 100644
index 0000000..cce03c0
--- /dev/null
+++ b/app/scraper/__init__.py
@@ -0,0 +1,3 @@
+from app.scraper.models import ScrapedListing
+
+__all__ = ["ScrapedListing"]
From cde5b1ffa1570f915649d814f69d0d23d69f987b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=D0=9F=D0=B0=D0=B2=D0=BB=D0=BE?=
<96915401+Rimus0cod@users.noreply.github.com>
Date: Mon, 5 Oct 2026 15:07:47 +0300
Subject: [PATCH 02/13] refactor: move scraped listing model to scraper package
---
app/scraper/models.py | 21 +++++++++++++++++++++
1 file changed, 21 insertions(+)
create mode 100644 app/scraper/models.py
diff --git a/app/scraper/models.py b/app/scraper/models.py
new file mode 100644
index 0000000..4c0dceb
--- /dev/null
+++ b/app/scraper/models.py
@@ -0,0 +1,21 @@
+from __future__ import annotations
+
+from dataclasses import dataclass
+
+
+@dataclass(slots=True)
+class ScrapedListing:
+ ad_id: str
+ title: str
+ price: str
+ location: str
+ size: str
+ link: str
+ image_url: str = ""
+ source_site: str = ""
+ phone: str = ""
+ seller_name: str = ""
+ ad_type: str = ""
+ contact_name: str = "-"
+ contact_email: str = "-"
+ date_seen: str = ""
From 52b23c485e3fbbb6cca221170d59a4f4d36eab7e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=D0=9F=D0=B0=D0=B2=D0=BB=D0=BE?=
<96915401+Rimus0cod@users.noreply.github.com>
Date: Mon, 5 Oct 2026 15:07:49 +0300
Subject: [PATCH 03/13] refactor: add scraper source package
---
app/scraper/sources/__init__.py | 3 +++
1 file changed, 3 insertions(+)
create mode 100644 app/scraper/sources/__init__.py
diff --git a/app/scraper/sources/__init__.py b/app/scraper/sources/__init__.py
new file mode 100644
index 0000000..27e2d5c
--- /dev/null
+++ b/app/scraper/sources/__init__.py
@@ -0,0 +1,3 @@
+from app.scraper.sources.alo import AloSourceParser
+
+__all__ = ["AloSourceParser"]
From c79df817d8431f3e1c36eeea7f506d0b9a08f60b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=D0=9F=D0=B0=D0=B2=D0=BB=D0=BE?=
<96915401+Rimus0cod@users.noreply.github.com>
Date: Mon, 5 Oct 2026 15:07:52 +0300
Subject: [PATCH 04/13] refactor: extract ALO source parser
---
app/scraper/sources/alo.py | 205 +++++++++++++++++++++++++++++++++++++
1 file changed, 205 insertions(+)
create mode 100644 app/scraper/sources/alo.py
diff --git a/app/scraper/sources/alo.py b/app/scraper/sources/alo.py
new file mode 100644
index 0000000..d09ed5f
--- /dev/null
+++ b/app/scraper/sources/alo.py
@@ -0,0 +1,205 @@
+from __future__ import annotations
+
+import re
+from typing import Protocol
+
+from bs4 import BeautifulSoup, Tag
+
+from app.scraper.models import ScrapedListing
+
+
+class AloParserContext(Protocol):
+ @staticmethod
+ def _attr_str(tag: Tag | None, name: str, default: str = "") -> str: ...
+
+ def _normalize_link(self, base_url: str, href: str | None) -> str: ...
+
+ def _clean_text(self, value: str) -> str: ...
+
+ def _title_from_url(self, link: str) -> str: ...
+
+ def _is_alo_listing_candidate(self, title: str, combined_text: str) -> bool: ...
+
+ def _extract_ad_id(self, link: str) -> str: ...
+
+ def _extract_size(self, text: str) -> str: ...
+
+ def _extract_image(self, card: Tag | None, base_url: str) -> str: ...
+
+ def _passes_filters(self, listing: ScrapedListing) -> bool: ...
+
+ def _detect_ad_type(self, seller_name: str) -> str: ...
+
+ def _extract_phone_from_text(self, text: str) -> str: ...
+
+
+class AloSourceParser:
+ def __init__(self, context: AloParserContext, source_site: str) -> None:
+ self._context = context
+ self._source_site = source_site
+
+ def parse_listing_page(self, html: str, base_url: str) -> list[ScrapedListing]:
+ soup = BeautifulSoup(html, "lxml")
+ cards = soup.select("div.ad_block_normal")
+ results: list[ScrapedListing] = []
+ seen_ids: set[str] = set()
+
+ for card in cards:
+ listing = self._parse_card(card, base_url)
+ if listing is None or listing.ad_id in seen_ids:
+ continue
+ seen_ids.add(listing.ad_id)
+ if self._context._passes_filters(listing):
+ results.append(listing)
+
+ return results
+
+ def _parse_card(self, card: Tag, base_url: str) -> ScrapedListing | None:
+ context = self._context
+ link_el = card.select_one("a.avn_seo[href], a.avn_image[href], a[href]")
+ if link_el is None:
+ return None
+
+ link = context._normalize_link(base_url, context._attr_str(link_el, "href"))
+ if not link:
+ return None
+
+ title_el = card.select_one("a.avn_seo[href]")
+ title = context._clean_text(
+ title_el.get_text(" ", strip=True)
+ if title_el is not None
+ else link_el.get_text(" ", strip=True)
+ )
+ if not title:
+ title = context._title_from_url(link)
+
+ image = card.select_one("a.avn_image img[alt], img[alt]")
+ image_alt = context._clean_text(context._attr_str(image, "alt"))
+ card_text = context._clean_text(card.get_text(" ", strip=True))
+ combined_text = context._clean_text(f"{title} {image_alt} {card_text}")
+
+ if not context._is_alo_listing_candidate(title=title, combined_text=combined_text):
+ return None
+
+ price_el = card.select_one(".avn_price")
+ price = context._clean_text(
+ price_el.get_text(" ", strip=True) if price_el is not None else ""
+ )
+
+ location_el = card.select_one(".avn_location")
+ location = context._clean_text(
+ location_el.get_text(" ", strip=True) if location_el is not None else ""
+ )
+
+ ad_id_match = re.search(
+ r"adrows_(\d{4,12})",
+ context._attr_str(card, "id"),
+ )
+ ad_id = ad_id_match.group(1) if ad_id_match else context._extract_ad_id(link)
+
+ return ScrapedListing(
+ ad_id=ad_id,
+ title=title,
+ price=price,
+ location=location,
+ size=context._extract_size(combined_text),
+ link=link,
+ image_url=context._extract_image(card, base_url),
+ source_site=self._source_site,
+ )
+
+ def enrich_detail(self, soup: BeautifulSoup, listing: ScrapedListing) -> None:
+ context = self._context
+
+ title_el = soup.select_one("h1.large-headline, h1")
+ if title_el is not None:
+ title = context._clean_text(title_el.get_text(" ", strip=True))
+ if title:
+ listing.title = title
+
+ price_text = self._extract_detail_price(soup)
+ if price_text:
+ listing.price = price_text
+
+ params = self._extract_params(soup)
+ if params.get("Местоположение"):
+ listing.location = params["Местоположение"]
+ if params.get("Квадратура"):
+ listing.size = params["Квадратура"].replace("\xa0", " ")
+
+ seller_name = self._extract_seller_name(soup)
+ if seller_name:
+ listing.seller_name = seller_name
+
+ contact_name = self._extract_contact_name(soup)
+ if contact_name:
+ listing.contact_name = contact_name
+
+ visible_phone = self._extract_phone(soup)
+ if visible_phone:
+ listing.phone = visible_phone
+
+ if soup.select_one(".contacts_wrapper_flex.has_agents"):
+ listing.ad_type = "agency"
+ elif listing.seller_name:
+ listing.ad_type = context._detect_ad_type(listing.seller_name)
+ else:
+ listing.ad_type = "private"
+
+ def _extract_detail_price(self, soup: BeautifulSoup) -> str:
+ for cell in soup.select(".ads-params-price"):
+ text = self._context._clean_text(cell.get_text(" ", strip=True))
+ if "€" in text or "лв" in text.lower():
+ return text.split("Цената е около", 1)[0].strip()
+ return ""
+
+ def _extract_params(self, soup: BeautifulSoup) -> dict[str, str]:
+ params: dict[str, str] = {}
+ for row in soup.select(".ads-params-row"):
+ title_el = row.select_one(".ads-param-title")
+ value_candidates = row.select(".ads-params-cell")
+ if title_el is None or len(value_candidates) < 2:
+ continue
+ title = self._context._clean_text(title_el.get_text(" ", strip=True))
+ value = self._context._clean_text(value_candidates[-1].get_text(" ", strip=True))
+ if title and value:
+ params[title] = value
+ return params
+
+ def _extract_seller_name(self, soup: BeautifulSoup) -> str:
+ header = soup.select_one(".contacts.header")
+ if header is None:
+ return ""
+
+ for candidate in header.stripped_strings:
+ value = self._context._clean_text(candidate)
+ if not value:
+ continue
+ if value in {
+ "Контакт с подателя",
+ "Контакт с подателя на обявата",
+ "Изпрати съобщение",
+ }:
+ continue
+ if value.endswith(".alo.bg"):
+ continue
+ if "Вход" in value and "Регистрация" in value:
+ continue
+ if "*" in value:
+ continue
+ return value
+ return ""
+
+ def _extract_contact_name(self, soup: BeautifulSoup) -> str:
+ el = soup.select_one(".agent_div .contact_value, .contact_value")
+ return self._context._clean_text(el.get_text(" ", strip=True) if el is not None else "")
+
+ def _extract_phone(self, soup: BeautifulSoup) -> str:
+ for span in soup.select(".contact_phone .ocd_span, .ocd_span"):
+ masked = self._context._clean_text(span.get_text(" ", strip=True))
+ if "X" in masked.upper():
+ continue
+ phone = self._context._extract_phone_from_text(masked)
+ if phone:
+ return phone
+ return ""
From 91db10d9f321560936bbb984524fa437c04f3fd0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=D0=9F=D0=B0=D0=B2=D0=BB=D0=BE?=
<96915401+Rimus0cod@users.noreply.github.com>
Date: Mon, 5 Oct 2026 15:08:08 +0300
Subject: [PATCH 05/13] refactor: delegate ALO parsing to source module
---
app/services/async_scraper.py | 187 +---------------------------------
1 file changed, 5 insertions(+), 182 deletions(-)
diff --git a/app/services/async_scraper.py b/app/services/async_scraper.py
index bfd746f..c822b2f 100755
--- a/app/services/async_scraper.py
+++ b/app/services/async_scraper.py
@@ -3,7 +3,6 @@
import asyncio
import random
import re
-from dataclasses import dataclass
from datetime import date
from typing import Any, Callable, Sequence
from urllib.parse import parse_qs, urljoin, urlparse
@@ -13,6 +12,8 @@
from app.core.config import Settings, SiteConfig
from app.core.logging import get_logger
+from app.scraper.models import ScrapedListing
+from app.scraper.sources.alo import AloSourceParser
extract_names: Callable[[str], list[str]] | None
extract_phone_numbers: Callable[[str], list[str]] | None
@@ -97,24 +98,6 @@
EMAIL_RE = re.compile(r"[A-Z0-9._%+-]+@[A-Z0-9.-]+\.[A-Z]{2,}", flags=re.I)
-@dataclass(slots=True)
-class ScrapedListing:
- ad_id: str
- title: str
- price: str
- location: str
- size: str
- link: str
- image_url: str = ""
- source_site: str = ""
- phone: str = ""
- seller_name: str = ""
- ad_type: str = ""
- contact_name: str = "-"
- contact_email: str = "-"
- date_seen: str = ""
-
-
class BaseScraper:
def __init__(self, site_config: SiteConfig, settings: Settings) -> None:
self.site_config = site_config
@@ -123,6 +106,7 @@ def __init__(self, site_config: SiteConfig, settings: Settings) -> None:
max(1, site_config.concurrency or settings.scrape_concurrency)
)
self._proxy_index = 0
+ self._alo_parser = AloSourceParser(self, site_config.name)
def _get_client_kwargs(self) -> dict[str, Any]:
headers = {
@@ -307,7 +291,7 @@ def _build_page_url(self, page: int) -> str:
def _parse_listing_page(self, html: str, base_url: str) -> list[ScrapedListing]:
parsers = {
"imoti.bg": self._parse_imoti_listing_page,
- "alo.bg": self._parse_alo_listing_page,
+ "alo.bg": self._alo_parser.parse_listing_page,
"dom.ria.com": self._parse_generic_anchor_page,
"olx.ua": self._parse_generic_anchor_page,
"lun.ua": self._parse_generic_anchor_page,
@@ -416,73 +400,6 @@ def _parse_imoti_card_exact(self, article: Tag, base_url: str) -> ScrapedListing
ad_type=self._detect_ad_type(seller_name),
)
- def _parse_alo_listing_page(self, html: str, base_url: str) -> list[ScrapedListing]:
- soup = BeautifulSoup(html, "lxml")
- cards = soup.select("div.ad_block_normal")
- results: list[ScrapedListing] = []
- seen_ids: set[str] = set()
-
- for card in cards:
- listing = self._parse_alo_card(card, base_url)
- if listing is None or listing.ad_id in seen_ids:
- continue
- seen_ids.add(listing.ad_id)
- if self._passes_filters(listing):
- results.append(listing)
-
- return results
-
- def _parse_alo_card(self, card: Tag, base_url: str) -> ScrapedListing | None:
- link_el = card.select_one("a.avn_seo[href], a.avn_image[href], a[href]")
- if link_el is None:
- return None
-
- link = self._normalize_link(base_url, self._attr_str(link_el, "href"))
- if not link:
- return None
-
- title_el = card.select_one("a.avn_seo[href]")
- title = self._clean_text(
- title_el.get_text(" ", strip=True)
- if title_el is not None
- else link_el.get_text(" ", strip=True)
- )
- if not title:
- title = self._title_from_url(link)
-
- image = card.select_one("a.avn_image img[alt], img[alt]")
- image_alt = self._clean_text(self._attr_str(image, "alt"))
- card_text = self._clean_text(card.get_text(" ", strip=True))
- combined_text = self._clean_text(f"{title} {image_alt} {card_text}")
-
- if not self._is_alo_listing_candidate(title=title, combined_text=combined_text):
- return None
-
- price_el = card.select_one(".avn_price")
- price = self._clean_text(price_el.get_text(" ", strip=True) if price_el is not None else "")
-
- location_el = card.select_one(".avn_location")
- location = self._clean_text(
- location_el.get_text(" ", strip=True) if location_el is not None else ""
- )
-
- ad_id_match = re.search(
- r"adrows_(\d{4,12})",
- self._attr_str(card, "id"),
- )
- ad_id = ad_id_match.group(1) if ad_id_match else self._extract_ad_id(link)
-
- return ScrapedListing(
- ad_id=ad_id,
- title=title,
- price=price,
- location=location,
- size=self._extract_size(combined_text),
- link=link,
- image_url=self._extract_image(card, base_url),
- source_site=self.site_config.name,
- )
-
def _parse_generic_cards(self, html: str, base_url: str) -> list[ScrapedListing]:
soup = BeautifulSoup(html, "lxml")
cards = soup.select(self.site_config.selectors.get("card", "article, li, div"))
@@ -602,7 +519,7 @@ async def _enrich_one(
if self.site_config.name == "imoti.bg":
self._enrich_imoti_detail(soup, listing)
elif self.site_config.name == "alo.bg":
- self._enrich_alo_detail(soup, listing)
+ self._alo_parser.enrich_detail(soup, listing)
else:
self._enrich_generic_detail(soup, listing)
@@ -690,100 +607,6 @@ def _enrich_imoti_detail(self, soup: BeautifulSoup, listing: ScrapedListing) ->
if listing.seller_name:
listing.ad_type = self._detect_ad_type(listing.seller_name)
- def _enrich_alo_detail(self, soup: BeautifulSoup, listing: ScrapedListing) -> None:
- title_el = soup.select_one("h1.large-headline, h1")
- if title_el is not None:
- title = self._clean_text(title_el.get_text(" ", strip=True))
- if title:
- listing.title = title
-
- price_text = self._extract_alo_detail_price(soup)
- if price_text:
- listing.price = price_text
-
- params = self._extract_alo_params(soup)
- if params.get("Местоположение"):
- listing.location = params["Местоположение"]
- if params.get("Квадратура"):
- listing.size = params["Квадратура"].replace("\xa0", " ")
-
- seller_name = self._extract_alo_seller_name(soup)
- if seller_name:
- listing.seller_name = seller_name
-
- contact_name = self._extract_alo_contact_name(soup)
- if contact_name:
- listing.contact_name = contact_name
-
- visible_phone = self._extract_alo_phone(soup)
- if visible_phone:
- listing.phone = visible_phone
-
- if soup.select_one(".contacts_wrapper_flex.has_agents"):
- listing.ad_type = "agency"
- elif listing.seller_name:
- listing.ad_type = self._detect_ad_type(listing.seller_name)
- else:
- listing.ad_type = "private"
-
- def _extract_alo_detail_price(self, soup: BeautifulSoup) -> str:
- for cell in soup.select(".ads-params-price"):
- text = self._clean_text(cell.get_text(" ", strip=True))
- if "€" in text or "лв" in text.lower():
- return text.split("Цената е около", 1)[0].strip()
- return ""
-
- def _extract_alo_params(self, soup: BeautifulSoup) -> dict[str, str]:
- params: dict[str, str] = {}
- for row in soup.select(".ads-params-row"):
- title_el = row.select_one(".ads-param-title")
- value_candidates = row.select(".ads-params-cell")
- if title_el is None or len(value_candidates) < 2:
- continue
- title = self._clean_text(title_el.get_text(" ", strip=True))
- value = self._clean_text(value_candidates[-1].get_text(" ", strip=True))
- if title and value:
- params[title] = value
- return params
-
- def _extract_alo_seller_name(self, soup: BeautifulSoup) -> str:
- header = soup.select_one(".contacts.header")
- if header is None:
- return ""
-
- for candidate in header.stripped_strings:
- value = self._clean_text(candidate)
- if not value:
- continue
- if value in {
- "Контакт с подателя",
- "Контакт с подателя на обявата",
- "Изпрати съобщение",
- }:
- continue
- if value.endswith(".alo.bg"):
- continue
- if "Вход" in value and "Регистрация" in value:
- continue
- if "*" in value:
- continue
- return value
- return ""
-
- def _extract_alo_contact_name(self, soup: BeautifulSoup) -> str:
- el = soup.select_one(".agent_div .contact_value, .contact_value")
- return self._clean_text(el.get_text(" ", strip=True) if el is not None else "")
-
- def _extract_alo_phone(self, soup: BeautifulSoup) -> str:
- for span in soup.select(".contact_phone .ocd_span, .ocd_span"):
- masked = self._clean_text(span.get_text(" ", strip=True))
- if "X" in masked.upper():
- continue
- phone = self._extract_phone_from_text(masked)
- if phone:
- return phone
- return ""
-
def _looks_like_real_seller_name(self, value: str) -> bool:
normalized = self._clean_text(value).lower()
if not normalized:
From fb70de9a85ce1c36792164b2c2e82efe3414b7f2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=D0=9F=D0=B0=D0=B2=D0=BB=D0=BE?=
<96915401+Rimus0cod@users.noreply.github.com>
Date: Mon, 5 Oct 2026 15:08:42 +0300
Subject: [PATCH 06/13] test: cover extracted ALO source parser
---
tests/test_alo_source_parser.py | 131 ++++++++++++++++++++++++++++++++
1 file changed, 131 insertions(+)
create mode 100644 tests/test_alo_source_parser.py
diff --git a/tests/test_alo_source_parser.py b/tests/test_alo_source_parser.py
new file mode 100644
index 0000000..69a0a19
--- /dev/null
+++ b/tests/test_alo_source_parser.py
@@ -0,0 +1,131 @@
+from __future__ import annotations
+
+import unittest
+
+from bs4 import BeautifulSoup
+
+from app.core.config import Settings, SiteConfig
+from app.services.async_scraper import BaseScraper
+
+
+class AloSourceParserTests(unittest.TestCase):
+ def setUp(self) -> None:
+ self.site = SiteConfig(
+ name="alo.bg",
+ base_url="https://www.alo.bg/obiavi/imoti-naemi/?page={page}",
+ max_pages=1,
+ allowed_domains=["alo.bg", "www.alo.bg"],
+ )
+ self.settings = Settings(
+ sites=[self.site],
+ city_filter=None,
+ scrape_detail_pages=False,
+ _env_file=None,
+ )
+ self.scraper = BaseScraper(self.site, self.settings)
+
+ def test_listing_page_is_delegated_to_alo_parser(self) -> None:
+ html = """
+
+
+
+
+
+
+
+ """
+
+ listings = self.scraper._parse_listing_page(
+ html,
+ base_url="https://www.alo.bg/obiavi/imoti-naemi/",
+ )
+
+ self.assertEqual(len(listings), 1)
+ listing = listings[0]
+ self.assertEqual(listing.ad_id, "123456")
+ self.assertEqual(listing.title, "Двустаен апартамент под наем")
+ self.assertEqual(listing.price, "700 €")
+ self.assertEqual(listing.location, "София, Център")
+ self.assertEqual(listing.size, "65 м²")
+ self.assertEqual(listing.source_site, "alo.bg")
+ self.assertEqual(
+ listing.link,
+ "https://www.alo.bg/obiava/123456/dvustaen-apartament-pod-naem",
+ )
+
+ def test_detail_enrichment_stays_source_specific(self) -> None:
+ listing = self.scraper._parse_listing_page(
+ """
+
+ """,
+ base_url="https://www.alo.bg/",
+ )[0]
+
+ soup = BeautifulSoup(
+ """
+
+ Обновен апартамент под наем
+ 720 € Цената е около 1400 лв
+
+
Местоположение
+
label
+
София, Лозенец
+
+
Квадратура
+
label
+
72 м²
+
+359 888 123 456
+
+
+ """,
+ "lxml",
+ )
+
+ self.scraper._alo_parser.enrich_detail(soup, listing)
+
+ self.assertEqual(listing.title, "Обновен апартамент под наем")
+ self.assertEqual(listing.price, "720 €")
+ self.assertEqual(listing.location, "София, Лозенец")
+ self.assertEqual(listing.size, "72 м²")
+ self.assertEqual(listing.seller_name, "Example Agency")
+ self.assertEqual(listing.contact_name, "Иван Иванов")
+ self.assertTrue(listing.phone)
+ self.assertEqual(listing.ad_type, "agency")
+
+
+if __name__ == "__main__":
+ unittest.main()
From 6616ac1824ff395995c35d279d45df548aee9649 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=D0=9F=D0=B0=D0=B2=D0=BB=D0=BE?=
<96915401+Rimus0cod@users.noreply.github.com>
Date: Mon, 5 Oct 2026 15:08:51 +0300
Subject: [PATCH 07/13] ci: validate extracted ALO parser
---
.github/workflows/ci-cd.yml | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/.github/workflows/ci-cd.yml b/.github/workflows/ci-cd.yml
index 5da7c7f..ebbe7bc 100755
--- a/.github/workflows/ci-cd.yml
+++ b/.github/workflows/ci-cd.yml
@@ -32,10 +32,13 @@ jobs:
poetry install --with dev
- name: Ruff
- run: poetry run ruff check app/ integrations/ utils.py
+ run: poetry run ruff check app/ integrations/ utils.py tests/test_alo_source_parser.py
- name: Ruff format check
- run: poetry run ruff format --check app/ integrations/ utils.py
+ run: poetry run ruff format --check app/ integrations/ utils.py tests/test_alo_source_parser.py
+
+ - name: ALO source parser regression test
+ run: poetry run python -m unittest discover -s tests -p "test_alo_source_parser.py"
typing:
runs-on: ubuntu-latest
From f1c05d6a585ac91c0ea56c646ce99c6fff36f12a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=D0=9F=D0=B0=D0=B2=D0=BB=D0=BE?=
<96915401+Rimus0cod@users.noreply.github.com>
Date: Mon, 5 Oct 2026 15:10:05 +0300
Subject: [PATCH 08/13] refactor: import ScrapedListing from scraper models
---
integrations/webhooks.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/integrations/webhooks.py b/integrations/webhooks.py
index 646cc0c..7f4a1e2 100755
--- a/integrations/webhooks.py
+++ b/integrations/webhooks.py
@@ -5,7 +5,7 @@
import httpx
from app.core.config import WebhookConfig
-from app.services.async_scraper import ScrapedListing
+from app.scraper.models import ScrapedListing
logger = logging.getLogger(__name__)
From c62a2099d79703f077fc1818b5e7abfa5c8030fe Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=D0=9F=D0=B0=D0=B2=D0=BB=D0=BE?=
<96915401+Rimus0cod@users.noreply.github.com>
Date: Mon, 5 Oct 2026 15:10:08 +0300
Subject: [PATCH 09/13] refactor: import ScrapedListing from scraper models
---
integrations/bitrix24.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/integrations/bitrix24.py b/integrations/bitrix24.py
index f4f9cc7..a08fcd8 100755
--- a/integrations/bitrix24.py
+++ b/integrations/bitrix24.py
@@ -4,7 +4,7 @@
import httpx
from app.core.config import Bitrix24Config, get_settings
-from app.services.async_scraper import ScrapedListing
+from app.scraper.models import ScrapedListing
logger = logging.getLogger(__name__)
From 8318d5ba452c2fe892dc414f8a9463ae34704c02 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=D0=9F=D0=B0=D0=B2=D0=BB=D0=BE?=
<96915401+Rimus0cod@users.noreply.github.com>
Date: Mon, 5 Oct 2026 15:10:11 +0300
Subject: [PATCH 10/13] refactor: import ScrapedListing from scraper models
---
integrations/amocrm.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/integrations/amocrm.py b/integrations/amocrm.py
index 2f4ecc6..b84fd98 100755
--- a/integrations/amocrm.py
+++ b/integrations/amocrm.py
@@ -5,7 +5,7 @@
import httpx
from app.core.config import AmoCrmConfig
-from app.services.async_scraper import ScrapedListing
+from app.scraper.models import ScrapedListing
logger = logging.getLogger(__name__)
From ee92a3998be2b5c767ad28b4a869ce873e261b88 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=D0=9F=D0=B0=D0=B2=D0=BB=D0=BE?=
<96915401+Rimus0cod@users.noreply.github.com>
Date: Mon, 5 Oct 2026 15:10:14 +0300
Subject: [PATCH 11/13] refactor: import ScrapedListing from scraper models
---
app/services/repository.py | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/app/services/repository.py b/app/services/repository.py
index 752a7b6..411bbc5 100755
--- a/app/services/repository.py
+++ b/app/services/repository.py
@@ -6,7 +6,8 @@
from typing import Any
from app.db.mysql import mysql_pool
-from app.services.async_scraper import ScrapedListing, to_listing_rows
+from app.scraper.models import ScrapedListing
+from app.services.async_scraper import to_listing_rows
logger = logging.getLogger(__name__)
_MISSING = object()
From 634c6cdcb3d097a4286acdde0334e7a21e47777e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=D0=9F=D0=B0=D0=B2=D0=BB=D0=BE?=
<96915401+Rimus0cod@users.noreply.github.com>
Date: Mon, 5 Oct 2026 15:10:16 +0300
Subject: [PATCH 12/13] refactor: import ScrapedListing from scraper models
---
app/scraper_worker.py | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/app/scraper_worker.py b/app/scraper_worker.py
index a638c48..d36976c 100755
--- a/app/scraper_worker.py
+++ b/app/scraper_worker.py
@@ -10,7 +10,8 @@
from app.core.config import Settings, get_settings
from app.core.logging import capture_exception, configure_logging, get_logger
from app.db.mysql import init_schema
-from app.services.async_scraper import MultiSiteScraper, ScrapedListing
+from app.scraper.models import ScrapedListing
+from app.services.async_scraper import MultiSiteScraper
from app.services.repository import upsert_leads
from integrations.amocrm import get_amocrm_integration
from integrations.bitrix24 import get_bitrix24_integration
From 3de79096b339224213ce15244a7cd6aeb33d9c9a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=D0=9F=D0=B0=D0=B2=D0=BB=D0=BE?=
<96915401+Rimus0cod@users.noreply.github.com>
Date: Mon, 5 Oct 2026 15:10:19 +0300
Subject: [PATCH 13/13] refactor: import ScrapedListing from scraper models
---
dashboard.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/dashboard.py b/dashboard.py
index ebeab38..49ce94b 100755
--- a/dashboard.py
+++ b/dashboard.py
@@ -13,7 +13,7 @@
from PIL import Image, ImageDraw, ImageFont
from app.db.mysql import mysql_pool
-from app.services.async_scraper import ScrapedListing
+from app.scraper.models import ScrapedListing
logger = logging.getLogger(__name__)
+
+