Python URL.domain方法代码示例

# 需要导入模块: from purl import URL [as 别名]
# 或者: from purl.URL import domain [as 别名]
def get_data(q_link):
    url = URL(q_link)
    if url.domain() not in ['quora.com', 'www.quora.com']:
        return 'error, not quora'

    url = URL(
        scheme='https',
        host='www.quora.com',
        path=url.path(),
        query='share=1').as_string()

    soup = BeautifulSoup(requests.get(url).text)

    question = {}
    question['url'] = url
    question['title'] = soup.find("div", {"class": "question_text_edit"}).text
    question['topics'] = [topic.text for topic in soup.find_all("div", {"class": "topic_list_item"})]
    question['details'] = soup.find("div", {"class": "question_details_text"}).text

    answers = []

    divs = soup.find_all("div", {"class": "pagedlist_item"})
    
    try:
        ans_count = soup.find("div", {"class": "answer_header_text"}).text.strip()
        count = int(re.match(r'(\d+) Answers', ans_count).groups()[0])
    except:
        return jsonify(question=question, answers=answers)

    question['answer_count'] = count

    count = len(divs) - 1 if count < 6 else 6
    for i in range(count):
        one_answer = {
            'votes': '-1',
            'rank': 0,
            'answer': ''
        }
        try:
            author = {}
            author['name'] = divs[i].find("div", {"class": "answer_user"}).find("span", {"class": "answer_user_wrapper"}).find("a", {"class": "user"}).string
            author['bio'] = divs[i].find("div", {"class": "answer_user"}).find("span", {"class": "answer_user_wrapper"}).find_all("span", {"class": "rep"})[1].find("span", {"class": "hidden"}).text
        except:
            author['name'] = 'Anonymous'
            author['bio'] = ''
        one_answer['author'] = author

        one_answer['votes'] = divs[i].find("span", {"class":"numbers"}).text

        html_block = divs[i].find("div", {"id": re.compile("(.*)_container")}).contents
        answer_html = ''
        for p in range(len(html_block) - 1):
            answer_html += str(html_block[p])
        one_answer['answer_html'] = answer_html
        one_answer['answer'] = divs[i].find("div", {"class": "answer_content"}).text
        one_answer['rank'] = i + 1
        answers.append(one_answer)

    return jsonify(question=question, answers=answers)

# 需要导入模块: from purl import URL [as 别名]
# 或者: from purl.URL import domain [as 别名]
def canonical_url(url, domain_check=True):
    """
    Ensure that the url contains the `http://mysite.com` part,
    particularly for requests made on the local dev server
    """
    current_site = Site.objects.get(id=settings.SITE_ID)
    if not url.startswith('http'):
        url = "http://%s" % os.path.join(current_site.domain, url.lstrip('/'))
    
    if domain_check:
        url_parts = URL(url)
        current_site_parts = URL(URL().domain(current_site.domain).as_string())
        if url_parts.subdomains()[-2:] != current_site_parts.subdomains()[-2:]:
            raise ValueError("Suspicious domain '%s' that differs from the "
                "current Site one '%s'" % (url_parts.domain(), current_site_parts.domain()))

    return url

# 需要导入模块: from purl import URL [as 别名]
# 或者: from purl.URL import domain [as 别名]
def get_questions(s_link):
    url = URL(s_link)
    if url.domain() not in ['quora.com', 'www.quora.com']:
        return 'error, not quora'

    url = URL(
        scheme='https',
        host='www.quora.com',
        path=url.path(),
        query='share=1').as_string()

    soup = BeautifulSoup(requests.get(url).text)

    topic = {}
    topic['url'] = url
    topic['title'] = soup.find("span", {"class": "TopicName"}).text

    questions = []
    divs = soup.find_all("div", {"class": "pagedlist_item"})
    count = len(divs) - 1
    for i in range(count):
        one_question = {
            'url': '',
			'title': ''
        }
        try:
            one_question['url'] = divs[i].find("a", {"class": "question_link"})['href']
            one_question['title'] = divs[i].find("a", {"class": "question_link"}).find("span", {"class": "link_text"}).text
        except:
            jsonify(topic=topic, questions=questions, parse_failure=one_question)
        one_question['url'] = URL(
            scheme='https',
            host='www.quora.com',
            path=one_question['url']).as_string()

        if one_question['title'] != "":
            questions.append(one_question)

    return jsonify(topic=topic, questions=questions)