Mirrors/kleinanzeigen-bot
1
0
Fork 0
mirror of https://github.com/Second-Hand-Friends/kleinanzeigen-bot.git synced 2026-03-12 10:31:50 +01:00
Code Issues Packages Projects Releases Wiki Activity

fix: ruff PLC0207 missing-maxsplit-arg

Browse Source
This commit is contained in:
sebthom
2025-06-09 17:15:49 +02:00
committed by Sebastian Thomschke
parent 67805e633f
commit 3978d85cb4
2 changed files with 13 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
src/kleinanzeigen_bot/extract.py
View File

@@ -112,13 +112,13 @@ class AdExtractor(WebScrapingMixin):
:param url: the URL to the ad page :param url: the URL to the ad page
:return: the ad ID, a (ten-digit) integer number :return: the ad ID, a (ten-digit) integer number
""" """
num_part = url.split("/")[-1] # suffix num_part = url.rsplit("/", maxsplit = 1)[-1] # suffix
id_part = num_part.split("-")[0] id_part = num_part.split("-", maxsplit = 1)[0]
try: try:
path = url.split("?", 1)[0] # Remove query string if present path = url.split("?", maxsplit = 1)[0] # Remove query string if present
last_segment = path.rstrip("/").split("/")[-1] # Get last path component last_segment = path.rstrip("/").rsplit("/", maxsplit = 1)[-1] # Get last path component
id_part = last_segment.split("-")[0] # Extract part before first hyphen id_part = last_segment.split("-", maxsplit = 1)[0] # Extract part before first hyphen
return int(id_part) return int(id_part)
except (IndexError, ValueError) as ex: except (IndexError, ValueError) as ex:
LOG.warning("Failed to extract ad ID from URL '%s': %s", url, ex) LOG.warning("Failed to extract ad ID from URL '%s': %s", url, ex)
@@ -340,8 +340,8 @@ class AdExtractor(WebScrapingMixin):
category_line = await self.web_find(By.ID, "vap-brdcrmb") category_line = await self.web_find(By.ID, "vap-brdcrmb")
category_first_part = await self.web_find(By.CSS_SELECTOR, "a:nth-of-type(2)", parent = category_line) category_first_part = await self.web_find(By.CSS_SELECTOR, "a:nth-of-type(2)", parent = category_line)
category_second_part = await self.web_find(By.CSS_SELECTOR, "a:nth-of-type(3)", parent = category_line) category_second_part = await self.web_find(By.CSS_SELECTOR, "a:nth-of-type(3)", parent = category_line)
cat_num_first = category_first_part.attrs["href"].split("/")[-1][1:] cat_num_first = category_first_part.attrs["href"].rsplit("/", maxsplit = 1)[-1][1:]
cat_num_second = category_second_part.attrs["href"].split("/")[-1][1:] cat_num_second = category_second_part.attrs["href"].rsplit("/", maxsplit = 1)[-1][1:]
category:str = cat_num_first + "/" + cat_num_second category:str = cat_num_first + "/" + cat_num_second
return category return category
@@ -371,15 +371,15 @@ class AdExtractor(WebScrapingMixin):
try: try:
price_str:str = await self.web_text(By.ID, "viewad-price") price_str:str = await self.web_text(By.ID, "viewad-price")
price:int | None = None price:int | None = None
match price_str.split()[-1]: match price_str.rsplit(maxsplit = 1)[-1]:
case "€": case "€":
price_type = "FIXED" price_type = "FIXED"
# replace('.', '') is to remove the thousands separator before parsing as int # replace('.', '') is to remove the thousands separator before parsing as int
price = int(price_str.replace(".", "").split()[0]) price = int(price_str.replace(".", "").split(maxsplit = 1)[0])
case "VB": case "VB":
price_type = "NEGOTIABLE" price_type = "NEGOTIABLE"
if price_str != "VB": # can be either 'X € VB', or just 'VB' if price_str != "VB": # can be either 'X € VB', or just 'VB'
price = int(price_str.replace(".", "").split()[0]) price = int(price_str.replace(".", "").split(maxsplit = 1)[0])
case "verschenken": case "verschenken":
price_type = "GIVE_AWAY" price_type = "GIVE_AWAY"
case _: case _:
@@ -490,7 +490,7 @@ class AdExtractor(WebScrapingMixin):
except TimeoutError: except TimeoutError:
LOG.info("No street given in the contact.") LOG.info("No street given in the contact.")
(zipcode, location) = address_text.split(" ", 1) (zipcode, location) = address_text.split(" ", maxsplit = 1)
contact["zipcode"] = zipcode # e.g. 19372 contact["zipcode"] = zipcode # e.g. 19372
contact["location"] = location # e.g. Mecklenburg-Vorpommern - Steinbeck contact["location"] = location # e.g. Mecklenburg-Vorpommern - Steinbeck

4
src/kleinanzeigen_bot/utils/web_scraping_mixin.py
View File

@@ -87,9 +87,9 @@ class WebScrapingMixin:
remote_port = 0 remote_port = 0
for arg in self.browser_config.arguments: for arg in self.browser_config.arguments:
if arg.startswith("--remote-debugging-host="): if arg.startswith("--remote-debugging-host="):
remote_host = arg.split("=", 2)[1] remote_host = arg.split("=", maxsplit = 1)[1]
if arg.startswith("--remote-debugging-port="): if arg.startswith("--remote-debugging-port="):
remote_port = int(arg.split("=", 2)[1]) remote_port = int(arg.split("=", maxsplit = 1)[1])
if remote_port > 0: if remote_port > 0:
LOG.info("Using existing browser process at %s:%s", remote_host, remote_port) LOG.info("Using existing browser process at %s:%s", remote_host, remote_port)