python - 请求无法保持登录 session

Question

我正在尝试从 mdpi.com 抓取一些电子邮件，电子邮件仅对登录用户可用。但当我尝试这样做时却失败了。我正进入(状态 注销时:

代码本身:

import requests
from bs4 import BeautifulSoup
import traceback

login_data = {'form[email]': '<a href="https://stackoverflow.com/cdn-cgi/l/email-protection" class="__cf_email__" data-cfemail="661e1e1e1e1e1e1e26010b070f0a4805090b" rel="noreferrer noopener nofollow">[email protected]</a>', 'form[password]': 'xxxxxxxxx', 'remember': 1,}
base_url = 'http://www.mdpi.com'
headers = {'user-agent': 'Mozilla/5.0 (Windows NT 6.1; rv:40.0) Gecko/20100101 Firefox/40.0'}

session = requests.Session()
session.headers = headers

# log_in
s = session.post('https://susy.mdpi.com/user/login', data=login_data)

print(s.text)
print(session.cookies)


def make_soup(url):
    try:
        r = session.get(url)
        soup = BeautifulSoup(r.content, 'lxml')
        return soup
    except:
        traceback.print_exc()
        return None


example_link = 'http://www.mdpi.com/search?journal=medsci&year_from=1996&year_to=2017&page_count=200&sort=relevance&view=default'


def article_finder(soup):
    one_page_articles_divs = soup.find_all('div', class_='article-content')
    for article_div in one_page_articles_divs:
        a_link = article_div.find('a', class_='title-link')
        link = base_url + a_link.get('href')
        print(link)
        article_soup = make_soup(link)
        grab_author_info(article_soup)


def grab_author_info(article_soup):

    # title of the article
    article_title = article_soup.find('h1', class_="title").text
    print(article_title)

    # affiliation
    affiliations_div = article_soup.find('div', class_='art-affiliations')
    affiliation_dict = {}
    aff_indexes = affiliations_div.find_all('div', class_='affiliation-item')
    aff_values = affiliations_div.find_all('div', class_='affiliation-name')
    for i, index in enumerate(aff_indexes):  # 0, 1
        affiliation_dict[int(index.text)] = aff_values[i].text

    # authors names
    authors_div = article_soup.find('div', class_='art-authors')
    authors_spans = authors_div.find_all('span', class_='inlineblock')
    for span in authors_spans:
        name_and_email = span.find_all('a')  # name and email
        name = name_and_email[0].text

        # email
        email = name_and_email[1].get('href')[7:]

        # affiliation_index
        affiliation_index = span.find('sup').text
        indexes = set()
        if len(affiliation_index) > 2:
            for i in affiliation_index.strip():
                try:
                    ind = int(i)
                    indexes.add(ind)
                except ValueError:
                    pass

        print(name)
        for index in indexes:
            print('affiliation =>', affiliation_dict[index])
        print('email: {}'.format(email))     


if __name__ == '__main__':
    article_finder(make_soup(example_link))

我应该做什么才能得到我想要的东西？

Answer 1

啊，这很简单，您还没有正确登录。如果您查看初始调用的响应，您将看到返回的是登录页面 HTML，而不是我的个人资料页面。原因是您没有提交表单上的隐藏 token 。

该解决方案请求登录页面，然后使用 lxml 或 BeautifulSoup 解析隐藏输入“form[_token]”。获取该值，然后将其添加到您的 login_data 有效负载中。

然后提交您的登录请求即可进入。