documents.py 文件源码

def get_related_document_ids(kamervraag_url):
    logger.info('get related antwoord id for url: ' + kamervraag_url)
    page = requests.get(kamervraag_url, timeout=60)
    tree = lxml.html.fromstring(page.content)
    relations_titles = tree.xpath('//div[@id="main-column"]//h2[@class="divisiekop1"]')
    overheidnl_document_ids = []
    for title_element in relations_titles:
        if title_element.text_content() == "Relaties":
            column_elements = title_element.getparent().xpath('//tr/td/p')
            next_is_antwoord_url = False
            for column_element in column_elements:
                if next_is_antwoord_url:
                    overheidnl_document_ids.append(column_element.text_content())
                    next_is_antwoord_url = False
                if column_element.text_content() == 'is beantwoord in':
                    next_is_antwoord_url = True
    return overheidnl_document_ids