How to download the PDF by using Selenium Module (FireFox) in Python 3

Question

I want to download a PDF which is from an Online-Magazin. In order to open it, must log in first. Then open the PDF and download it.

The following is my code. It can login to the page and the PDF can also be open. But the PDF can not be downloaded since I am not sure how to simulate the click on Save. I use FireFox.

import os, time
from selenium import webdriver
from bs4 import BeautifulSoup

# Use firefox dowmloader to get file
fp = webdriver.FirefoxProfile()
fp.set_preference("browser.download.folderList",2)
fp.set_preference("browser.download.manager.showWhenStarting",False)
fp.set_preference("browser.download.dir", 'D:/eBooks/Stocks_andCommodities/2008/Jul/')
fp.set_preference("browser.helperApps.neverAsk.saveToDisk", "application/pdf")
fp.set_preference("pdfjs.disabled", "true")

# disable Adobe Acrobat PDF preview plugin
fp.set_preference("plugin.scan.plid.all", "false")
fp.set_preference("plugin.scan.Acrobat", "99.0")

browser = webdriver.Firefox(firefox_profile=fp)

# Get the login web page
web_url = 'http://technical.traders.com/sub/sublogin2.asp'
browser.get(web_url)

# SImulate the authentication
user_name = browser.find_element_by_css_selector('#SubID > input[type="text"]')
user_name.send_keys("thomas2003@test.net")
password = browser.find_element_by_css_selector('#SubName > input[type="text"]')
password.send_keys("LastName")
time.sleep(2)
submit = browser.find_element_by_css_selector('#SubButton > input[type="submit"]')
submit.click()
time.sleep(2)

# Open the PDF for downloading
url = 'http://technical.traders.com/archive/articlefinal.asp?file=\V26\C07\\131INTR.pdf'
browser.get(url)
time.sleep(10)

# How to simulate the Clicking to Save/Download the PDF here?

Answer 1

您不应该在浏览器中打开文件。找到文件网址后。获取所有cookie的请求会话

def get_request_session(driver):
    import requests
    session = requests.Session()
    for cookie in driver.get_cookies():
        session.cookies.set(cookie['name'], cookie['value'])

    return session

进行会话后，您可以使用相同的文件下载文件

url = 'http://technical.traders.com/archive/articlefinal.asp?file=\V26\C07\\131INTR.pdf'
session = get_request_session(driver)
r = session.get(url, stream=True)
chunk_size = 2000
with open('/tmp/mypdf.pdf', 'wb') as file:
    for chunk in r.iter_content(chunk_size):
        file.write(chunk)