Python BeautifulSoup：迭代元素列表并按类提取文本

过滤到section，然后 Select class_:

from typing import Iterator

import bs4
from requests import Session


STRAINER = bs4.SoupStrainer(name='section', class_='item authors')


def fetch_authors(session: Session, article: int) -> bs4.ResultSet:
    with session.get(
        url=f'https://rpmgf.pt/ojs/index.php/rpmgf/article/view/{article}',
    ) as resp:
        resp.raise_for_status()
        dom = bs4.BeautifulSoup(markup=resp.text, parse_only=STRAINER, features='lxml')
    return dom.find_all(name='span', class_='name')


def main() -> None:
    with Session() as session:
        for author_tag in fetch_authors(session=session, article=13494):
            print(author_tag.text.strip())


if __name__ == '__main__':
    main()

Maria João Gonçalves
Clara Fonseca
Inês Pintalhão
Rodrigo Costa
Ana Calafate
Manuel Henriques

或者，如果您还关心从属关系:

from typing import Iterator

import bs4
from requests import Session


STRAINER = bs4.SoupStrainer(name='section', class_='item authors')


def fetch_authors(session: Session, article: int) -> Iterator[tuple[str, str | None]]:
    with session.get(
        url=f'https://rpmgf.pt/ojs/index.php/rpmgf/article/view/{article}',
    ) as resp:
        resp.raise_for_status()
        dom = bs4.BeautifulSoup(markup=resp.text, parse_only=STRAINER)  # , features='lxml')

    for name in dom.find_all(name='span', class_='name'):
        # Search through siblings for a matching affiliation tag
        for affiliation in name.find_next_siblings(name='span'):
            name_str = name.text.strip()
            class_ = affiliation.attrs.get('class', ())[0]
            if class_ == 'affiliation':
                # If we've found an affiliation class on the soonest span sibling, use it
                yield name_str, affiliation.text.strip()
                break
            elif class_ == 'name':
                # If we've encountered the next name, there is no affiliation.
                yield name_str, None
                break
        else:
            # If there are no span siblings, there is no affiliation.
            yield name.text.strip(), None


def main() -> None:
    with Session() as session:
        print('An article with some authors missing affiliation:')
        for name, affiliation in fetch_authors(session=session, article=13545):
            print(f'{name} ({affiliation})')
        print()

        print('An article with authors all having affiliation:')
        for name, affiliation in fetch_authors(session=session, article=13494):
            print(f'{name} ({affiliation})')
        print()


if __name__ == '__main__':
    main()

An article with some authors missing affiliation:
Andreia Oliveira (Médica)
Rita Paraíso (None)
Paola Lobão (None)
Vanessa Guerreiro (None)

An article with authors all having affiliation:
Maria João Gonçalves (USF Garcia de Orta)
Clara Fonseca (Assistente Graduada de Medicina Geral e Familiar na USF Garcia de Orta, ACeS Porto Ocidental)
Inês Pintalhão (Assistente de Medicina Geral e Familiar da USF Garcia de Orta, ACes Porto Ocidental)
Rodrigo Costa (Interno de Formação Específica de Medicina Geral e Familiar da USF Garcia de Orta, ACeS Porto Ocidental)
Ana Calafate (Assistente de Medicina Geral e Familiar da USF Garcia de Orta, ACeS Porto Ocidental)
Manuel Henriques (Assistente de Medicina Geral e Familiar da USF Garcia de Orta, ACeS Porto Ocidental)