3b5d9fd940
Features: - FastAPI backend for scraping attendance and journey book data - Deterministic kilometer distribution with random variance - Refueling form filling with km values - Next.js frontend with date range selector - Docker deployment setup 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
74 lines
3.1 KiB
Python
74 lines
3.1 KiB
Python
import re
|
|
import requests
|
|
from bs4 import BeautifulSoup
|
|
import pandas as pd
|
|
from typing import Dict, Any
|
|
|
|
|
|
class JourneybookScraper:
|
|
def __init__(self, username: str, password: str, vehicle_registration: str = "4SH1148"):
|
|
self.username = username
|
|
self.password = password
|
|
self.vehicle_registration = vehicle_registration
|
|
self.base_url = "https://kj.colsys.cz/prehled_mesic.php"
|
|
|
|
@staticmethod
|
|
def normalize_date(date_str: str) -> str:
|
|
return re.sub(r'\s+', '', date_str)
|
|
|
|
def scrape_month(self, month: str) -> pd.DataFrame:
|
|
"""
|
|
Scrape journeybook data for a given month.
|
|
Returns DataFrame with columns: Datum, Počáteční stav, Koncový stav, Ujeto [km], Natankováno [l|kg]
|
|
"""
|
|
url = f"{self.base_url}?rz={self.vehicle_registration}&den={month}-01"
|
|
|
|
response = requests.get(url, auth=(self.username, self.password), verify=False)
|
|
response.raise_for_status()
|
|
|
|
soup = BeautifulSoup(response.content, 'html.parser')
|
|
table = soup.find('table', class_='table table-striped table-bordered table-condensed table-sm')
|
|
|
|
if not table:
|
|
raise ValueError("Journeybook table not found")
|
|
|
|
headers = [th.text.strip() for th in table.find('thead').find_all('th')]
|
|
headers = [header.replace(" ", "") for header in headers]
|
|
|
|
columns_to_keep = ["Datum", "Počátečnístav", "Koncovýstav", "Ujeto[km]"]
|
|
new_headers = ["Datum", "Počáteční stav", "Koncový stav", "Ujeto [km]", "Natankováno [l|kg]"]
|
|
|
|
for col in columns_to_keep:
|
|
if col not in headers:
|
|
raise ValueError(f"Column '{col}' not found. Headers: {headers}")
|
|
|
|
rows = []
|
|
for row in table.find('tbody').find_all('tr'):
|
|
if "Tankováno" in row.text:
|
|
refuel_text = row.text.strip()
|
|
amount_match = re.search(r'natankováno\s(\d+\.\d+)\s\[l\|kg\]', refuel_text)
|
|
amount = amount_match.group(1) if amount_match else ""
|
|
rows.append([""] * len(columns_to_keep) + [amount])
|
|
elif row.find('form'):
|
|
cells = []
|
|
for cell in row.find_all('td'):
|
|
input_field = cell.find('input')
|
|
if input_field:
|
|
cells.append(input_field.get('value', ''))
|
|
else:
|
|
if headers[len(cells)] == "Datum":
|
|
date_match = re.search(r'\d{1,2}\.\s\d{1,2}\.\s\d{4}', cell.text.strip())
|
|
if date_match:
|
|
cells.append(self.normalize_date(date_match.group()))
|
|
else:
|
|
cells.append(cell.text.strip())
|
|
else:
|
|
cells.append(cell.text.strip())
|
|
|
|
filtered_cells = [cells[headers.index(col)] for col in columns_to_keep]
|
|
filtered_cells.append("")
|
|
rows.append(filtered_cells)
|
|
|
|
df = pd.DataFrame(rows, columns=new_headers)
|
|
return df
|