Files
sisvietnamvn_01/sisvietnamvn_main/check_files.py
T

43 lines
1.5 KiB
Python

import csv
import xml.etree.ElementTree as ET
import sys
import os
csv_file = '/home/x79/sisvietnamvn_01/sisvietnamvn_Trang chính thức hiện tại/DS_BacSi/DANH SÁCH BÁC SĨ NGỒI PHÒNG KHÁM_THÔNG TIN CHI TIẾT_FULL.csv'
xml_file = '/home/x79/sisvietnamvn_01/sisvietnamvn_Trang chính thức hiện tại/DS_BacSi/bnhvinakhoaquctsiscnth.WordPress.2026-07-28 (5).xml'
print("CSV Headers:")
with open(csv_file, 'r', encoding='utf-8-sig') as f:
reader = csv.reader(f)
print(next(reader))
print("\nXML meta keys for first doctor:")
tree = ET.parse(xml_file)
root = tree.getroot()
ns = {
'wp': 'http://wordpress.org/export/1.2/',
'content': 'http://purl.org/rss/1.0/modules/content/'
}
for channel in root.findall('channel'):
for item in channel.findall('item'):
post_type = item.find('wp:post_type', ns)
if post_type is not None and post_type.text == 'doctor':
print('Title:', item.find('title').text)
for meta in item.findall('wp:postmeta', ns):
key = meta.find('wp:meta_key', ns)
val = meta.find('wp:meta_value', ns)
if key is not None and val is not None and not key.text.startswith('_'):
print(f" {key.text}")
break
# Count doctors in each
print(f"\nTotal items in XML:")
c = 0
for channel in root.findall('channel'):
for item in channel.findall('item'):
post_type = item.find('wp:post_type', ns)
if post_type is not None and post_type.text == 'doctor':
c += 1
print(c)