mirror of
https://github.com/mblanke/Gov_Travel_App.git
synced 2026-03-01 14:10:22 -05:00
mblanke
969ba062f7
- Implemented alphabet navigation (A-Z) for NJC international rates page - Added request delays (2s) and retry logic with exponential backoff to avoid server timeouts - Added error handling for pages without tables - Installed html5lib for better HTML parsing - Now scrapes 233 countries (up from 15) with 104 unique currencies - Total 11,628 international rate entries collected - Added verification scripts to check all countries and their currencies - Fixed currency extraction working perfectly for EUR, USD, CAD, AUD, ARS, and 99+ other currencies
36 lines
1.0 KiB
Python
36 lines
1.0 KiB
Python
"""Check what's on the NJC international page"""
|
|
import sys
|
|
sys.path.insert(0, 'src')
|
|
|
|
from gov_travel.scrapers import fetch_html
|
|
from bs4 import BeautifulSoup
|
|
|
|
url = "https://www.njc-cnm.gc.ca/directive/app_d.php?lang=en"
|
|
print(f"Fetching: {url}\n")
|
|
|
|
html = fetch_html(url)
|
|
soup = BeautifulSoup(html, 'html.parser')
|
|
|
|
# Count tables
|
|
tables = soup.find_all('table')
|
|
print(f"Total tables found: {len(tables)}")
|
|
|
|
# Find all headings before tables (country names)
|
|
countries = set()
|
|
for table in tables:
|
|
heading = table.find_previous(['h1', 'h2', 'h3', 'h4'])
|
|
if heading:
|
|
text = heading.get_text(strip=True)
|
|
# Extract country name (before " - Currency:")
|
|
if ' - Currency:' in text:
|
|
country = text.split(' - Currency:')[0].strip()
|
|
countries.add(country)
|
|
|
|
print(f"\nUnique countries found: {len(countries)}")
|
|
print("\nFirst 20 countries:")
|
|
for i, country in enumerate(sorted(countries)[:20], 1):
|
|
print(f"{i:2}. {country}")
|
|
|
|
if len(countries) > 20:
|
|
print(f"\n... and {len(countries) - 20} more")
|