js-web-scraper 20260721175813.dev0__tar.gz → 20260801155736.dev0__tar.gz

{js_web_scraper-20260721175813.dev0 → js_web_scraper-20260801155736.dev0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: js-web-scraper
-Version: 20260721175813.dev0
+Version: 20260801155736.dev0
 Summary: Customizable Web Scrapper to get alerts when criteria is met on web sites.
 Author-email: jnstockley <jnstockley@users.noreply.github.com>
 Project-URL: Homepage, https://github.com/jnstockley/web-scraper
@@ -12,7 +12,7 @@ Requires-Python: <4.0,>=3.13
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: beautifulsoup4==4.15.0
-Requires-Dist: pandas==3.0.4
+Requires-Dist: pandas==3.0.5
 Requires-Dist: python-dotenv==1.2.2
 Requires-Dist: tls-client==1.0.1
 Dynamic: license-file

{js_web_scraper-20260721175813.dev0 → js_web_scraper-20260801155736.dev0}/pyproject.toml

@@ -1,12 +1,12 @@
 [project]
 name = "js-web-scraper"
-version = "20260721175813.dev"
+version = "20260801155736.dev"
 description = "Customizable Web Scrapper to get alerts when criteria is met on web sites."
 readme = "README.md"
 requires-python = ">=3.13, <4.0"
 dependencies = [
     "beautifulsoup4==4.15.0",
-    "pandas==3.0.4",
+    "pandas==3.0.5",
     "python-dotenv==1.2.2",
     "tls-client==1.0.1",
 ]

{js_web_scraper-20260721175813.dev0 → js_web_scraper-20260801155736.dev0}/src/email_sender.py

@@ -34,7 +34,7 @@ def send_email_str(text: str):
     __send_email__("Tesla NACS Website Update", html)
 
 
-def __send_email__(subject: str, html: str, attachment: StringIO = None):
+def __send_email__(subject: str, html: str, attachment: StringIO | None = None):
     load_dotenv()
     sender_email = os.environ["SENDER_EMAIL"]
     from_email = os.environ["FROM_EMAIL"]

{js_web_scraper-20260721175813.dev0 → js_web_scraper-20260801155736.dev0}/src/healthcheck.py

@@ -1,4 +1,5 @@
 import os
+import sys
 
 from dotenv import load_dotenv
 
@@ -19,4 +20,4 @@ if __name__ == "__main__":
             up_to_date = False
 
     if not up_to_date:
-        exit(1)
+        sys.exit(1)

{js_web_scraper-20260721175813.dev0 → js_web_scraper-20260801155736.dev0}/src/js_web_scraper.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: js-web-scraper
-Version: 20260721175813.dev0
+Version: 20260801155736.dev0
 Summary: Customizable Web Scrapper to get alerts when criteria is met on web sites.
 Author-email: jnstockley <jnstockley@users.noreply.github.com>
 Project-URL: Homepage, https://github.com/jnstockley/web-scraper
@@ -12,7 +12,7 @@ Requires-Python: <4.0,>=3.13
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: beautifulsoup4==4.15.0
-Requires-Dist: pandas==3.0.4
+Requires-Dist: pandas==3.0.5
 Requires-Dist: python-dotenv==1.2.2
 Requires-Dist: tls-client==1.0.1
 Dynamic: license-file

{js_web_scraper-20260721175813.dev0 → js_web_scraper-20260801155736.dev0}/src/js_web_scraper.egg-info/requires.txt

@@ -1,4 +1,4 @@
 beautifulsoup4==4.15.0
-pandas==3.0.4
+pandas==3.0.5
 python-dotenv==1.2.2
 tls-client==1.0.1

{js_web_scraper-20260721175813.dev0 → js_web_scraper-20260801155736.dev0}/src/main.py

@@ -1,10 +1,10 @@
-import time
 import os
 import sys
+import time
 
 from dotenv import load_dotenv
 
-from src.scrapers import text, diff, cars_com
+from src.scrapers import cars_com, diff, text
 from util.healthcheck import healthcheck
 from util.logging import logger
 
@@ -23,7 +23,7 @@ def main():
                 logger.info(f"Checking URL: {url} for text: {scrape_text}")
                 text.scrape(url, scrape_text)
             case "diff":
-                percentage = float(os.environ.get("PERCENTAGE", 10))
+                percentage = float(os.environ.get("PERCENTAGE", "10"))
                 logger.info("Using diff scraper")
                 logger.info(f"Checking URL: {url}")
                 diff.scrape(url, percentage)

{js_web_scraper-20260721175813.dev0 → js_web_scraper-20260801155736.dev0}/src/scrapers/diff.py

@@ -1,3 +1,5 @@
+from difflib import ndiff
+
 from src.email_sender import send_email_str
 from src.scrapers import generic
 from src.scrapers.generic import (
@@ -5,8 +7,6 @@ from src.scrapers.generic import (
     save_data_compressed,
     save_healthcheck_file,
 )
-from difflib import ndiff
-
 from src.util.logging import logger
 
 
@@ -34,7 +34,7 @@ def scrape(url: str, percentage: float = 10):
 
 def compare(old: str, new: str) -> float:
     diff = list(ndiff(old.splitlines(), new.splitlines()))
-    changes = sum(1 for line in diff if line.startswith("+ ") or line.startswith("- "))
+    changes = sum(1 for line in diff if line.startswith(("+ ", "- ")))
     total_lines = max(len(old.splitlines()), len(new.splitlines()))
     difference_percentage = (changes / total_lines) * 100 if total_lines > 0 else 0
     logger.debug(

{js_web_scraper-20260721175813.dev0 → js_web_scraper-20260801155736.dev0}/src/scrapers/generic.py

@@ -5,12 +5,11 @@ from typing import Literal
 
 import pandas as pd
 import tls_client
-from typing_extensions import Optional, Union
 
 from src.util.logging import logger
 
 
-def create_tls_session(proxy: str = None) -> tls_client.Session:
+def create_tls_session(proxy: str | None = None) -> tls_client.Session:
     """
     Create a TLS session with the given proxy, if applicable.
     :param proxy: Proxy string in the format https://user:pass@ip:port
@@ -30,15 +29,15 @@ def make_tls_request(
     method: Literal["GET", "POST", "PUT", "DELETE"],
     url: str,
     session: tls_client.Session,
-    params: Optional[dict] = None,
-    data: Optional[Union[str, dict]] = None,
-    headers: Optional[dict] = None,
-    cookies: Optional[dict] = None,
-    json: Optional[dict] = None,
-    allow_redirects: Optional[bool] = False,
-    insecure_skip_verify: Optional[bool] = False,
-    timeout_seconds: Optional[int] = None,
-    proxy: Optional[dict] = None,
+    params: dict | None = None,
+    data: str | dict | None = None,
+    headers: dict | None = None,
+    cookies: dict | None = None,
+    json: dict | None = None,
+    allow_redirects: bool | None = False,
+    insecure_skip_verify: bool | None = False,
+    timeout_seconds: int | None = None,
+    proxy: dict | None = None,
 ):
     """
     Make a TLS request with the given parameters.
@@ -75,9 +74,9 @@ def make_tls_request(
         if "application/json" in response_headers.get("Content-Type", ""):
             try:
                 return response.json()
-            except ValueError as e:
+            except ValueError:
                 logger.error("Response content is not valid JSON")
-                raise e
+                raise
         return response.content.decode(encoding="utf-8")
 
     raise ConnectionError(f"Request failed with status code {response.status_code}")

{js_web_scraper-20260721175813.dev0 → js_web_scraper-20260801155736.dev0}/src/util/healthcheck.py

@@ -1,6 +1,8 @@
+import sys
+
 from util.logging import logger
 
 
 def healthcheck() -> bool:
     logger.info("Healthcheck passed!")
-    exit(0)
+    sys.exit(0)

{js_web_scraper-20260721175813.dev0 → js_web_scraper-20260801155736.dev0}/src/scrapers/cars_com.py

@@ -1,8 +1,8 @@
-from dataclasses import dataclass
 import json
+from dataclasses import dataclass
 
-from bs4 import BeautifulSoup
 import pandas as pd
+from bs4 import BeautifulSoup
 from pandas import DataFrame
 
 from src.email_sender import send_email