# -*- coding: utf-8 -*-
# @Time    : 2026/1/13 16:08
# @Author  : zhaoxiangpeng
# @File    : test_more_so.py

from parsel import Selector

TABLE_HEAD_EN = ['src_db', 'title', 'author', 'org', 'journal', 'keyword', 'abstract', 'pub_time', 'first_duty', 'fund', 'year', 'volum', 'issue', 'page', 'classification_code', 'issn', 'url', 'doi']


def test_parser():
    with open('Y:\cnki-metadata\CNKI-20260112161602991.xls', encoding='utf-8') as f:
        data = f.read()
        print(data)
    selector = Selector(data)
    rows = selector.xpath(r'//tr')
    for row in rows[1:]:
        cols = row.xpath('./td')
        row_datas = []
        for col in cols:
            col_data = col.xpath('string(.)').get().strip()
            row_datas.append(col_data)
        data = dict(zip(TABLE_HEAD_EN, row_datas))
        if data.get('src_db') == 'SrcDatabase-来源库':
            continue
        print(data)