#!/usr/bin/env python3
"""Test ningguo content parsing"""
import sys
sys.path.insert(0, '/root')
from crawl_ningguo_tzgg import get_soup, extract_content

soup = get_soup('http://www.ningguo.gov.cn/News/show/1720345.html')
if soup:
    title, content, pub_date, attachments = extract_content(soup)
    print('TITLE:', title)
    print('DATE:', pub_date)
    print('ATTACH:', len(attachments))
    segs = content.split('\n\n')
    print('SEGMENTS:', len(segs))
    print('=' * 40)
    print(content[:2000])
else:
    print('FAILED to get soup')