Python 3.x 还有一个Python编码问题

我尝试了以下代码：

def process_request(url):
    req = Request(url, headers={'User-Agent': 'Mozilla/5.0'})
    return urlopen(req).read()

def get_links():
    url = c.first_url
    html = process_request(url)
    details_pages = []
    soup = BeautifulSoup(html, 'html.parser')
    links = soup.select(".pagelist-bar  a")
    print(links)
    for l in links:
        print(l)
        if l.has_attr('href'):
            href_ = l['href']
            detail = c.base_url + href_
            logging.info("Page with List of persons: %s", detail)
            details_pages.append(detail)
    return details_pages

def person_urls():
    pages = get_links()
    for l in pages:
        print("link: %s", l)
        doc = process_request(l)
        soup = BeautifulSoup(doc, 'html.parser')
        fichas = soup.select(".ficha")
        print(fichas)

在此url中：

无论我使用什么策略，这一行：

<a href="/es/colaboracion/buscados/index.html?buscar=si&category=abcd&notshown=">

---

有人能帮我吗？

也许你应该试着在你的BeautifulSoup呼叫中用

html

替换

html.parser

：

soup = BeautifulSoup(html, 'html')
links = soup.select(".pagelist-bar  a")
#Ouptut
for x in links:
    print(x.get('href'))

输出：

/es/colaboracion/buscados/index.html?pagina=1&buscar=si&category=&notshown=
/es/colaboracion/buscados/index.html?pagina=2&buscar=si&category=&notshown=
/es/colaboracion/buscados/index.html?pagina=3&buscar=si&category=&notshown=
/es/colaboracion/buscados/index.html?pagina=4&buscar=si&category=&notshown=

soup = BeautifulSoup(html, 'html')
links = soup.select(".pagelist-bar  a")
#Ouptut
for x in links:
    print(x.get('href'))

/es/colaboracion/buscados/index.html?pagina=1&buscar=si&category=&notshown=
/es/colaboracion/buscados/index.html?pagina=2&buscar=si&category=&notshown=
/es/colaboracion/buscados/index.html?pagina=3&buscar=si&category=&notshown=
/es/colaboracion/buscados/index.html?pagina=4&buscar=si&category=&notshown=