Develop Reference

Headless mode disable python web file downloading

I aim to download web files while in headless mode. My program downloads perfectly when NOT in headless mode, but once I add the constraint not to show MS Edge opening, the downloading is disregarded.
import time
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import Select
driver = webdriver.Edge()
driver.get("URL")
id_box = driver.find_element(By.ID,"...")
pw_box = driver.find_element(By.ID,"...")
id_box.send_keys("...")
pw_box.send_keys("...")
log_in = driver.find_element(By.ID,"...")
log_in.click()
time.sleep(0.1) # If not included, get error: "Unable to locate element"
drop_period = Select(driver.find_element(By.ID,"..."))
drop_period.select_by_index(1)
drop_consul = Select(driver.find_element(By.ID,"..."))
drop_consul.select_by_visible_text("...")
drop_client = Select(driver.find_element(By.ID,"..."))
drop_client.select_by_index(1)
# Following files do not download with headless inculded:
driver.find_element(By.XPATH, "...").click()
driver.find_element(By.XPATH, "...").click()

In that case, you might try downloading the file using the direct link (to the file) and python requests.
You'll need to get the url, by parsing the elemt its href:
Downloading and saving a file from url should work as following then:
import requests as req
remote_url = 'http://www.example.com/file.txt'
local_file_name = 'my_file.txt'
data = req.get(remote_url)
# Save file data to local copy
with open(local_file_name, 'wb')as file:
file.write(data.content)
resource

There are different headless modes for Chrome. If you want to download files, use one of the special ones.
For Chrome 109 and above, use:
options.add_argument("--headless=new")
For Chrome 108 and below, use:
options.add_argument("--headless=chrome")
Reference: https://github.com/chromium/chromium/commit/e9c516118e2e1923757ecb13e6d9fff36775d1f4

Downloading files in headless mode works for me on MicrosoftEdge version 110.0.1587.41 using following options:
MicrosoftEdge: [{
"browserName": "MicrosoftEdge",
"ms:edgeOptions": {
args: ['--headless=new'],
prefs: {
"download.prompt_for_download": false,
"plugins.always_open_pdf_externally": true,
'download.default_directory': "dlFolder"
}
},
}]
Nothing worked until I added the option '--headless=new'
N.B: Tested on a Mac environment using webdriverIO

How to bypass the alert window while downloading a zipfile?

If I open the link: https://dibbs2.bsm.dla.mil/Downloads/RFQ/Archive/ca210731.zip
This link shows the window and I need to press the OK button and it downloads the file.
The alert is not from the browser, it is from the page itself.
But When I tried the script:
from io import BytesIO
from zipfile import ZipFile
import requests
def get_zip(file_url):
url = requests.get(file_url)
zipfile = ZipFile(BytesIO(url.content))
zipfile.extractall("")
file_link ='https://dibbs2.bsm.dla.mil/Downloads/RFQ/Archive/ca210731.zip'
get_zip(file_link)
This throws the error:
zipfile.BadZipFile: File is not a zip file
And when I tried:
import requests
url = r'https://dibbs2.bsm.dla.mil/Downloads/RFQ/Archive/ca210731.zip'
output = r'downloadedfile.zip'
r = requests.get(url)
with open(output, 'wb') as f:
f.write(r.content)
This downloads the content of the page showing the OK button.
Any idea how to solve this:, the link downloads the zip file.

I believe you are accepting answer using selenium, Here's what you can do using selenium :
from selenium import webdriver
from selenium.webdriver.firefox.options import Options
profile = webdriver.FirefoxProfile()
profile.set_preference("browser.download.folderList",1)
# 0 for desktop
# 1 for default download folder
# 2 for specific folder
# You can specify directory by using profile.set_preference("browser.download.dir","<>")
profile.set_preference("browser.helperApps.neverAsk.saveToDisk", "application/octet-stream")
profile.set_preference("browser.helperApps.alwaysAsk.force", False);
# If you don't have some download manager then you can remove these
profile.set_preference("browser.download.manager.showWhenStarting",False)
profile.set_preference("browser.download.manager.useWindow", False);
profile.set_preference("browser.download.manager.focusWhenStarting", False);
profile.set_preference("browser.download.manager.alertOnEXEOpen", False);
profile.set_preference("browser.download.manager.showAlertOnComplete", False);
driver=webdriver.Firefox(firefox_profile=profile,executable_path="<>")
driver.get("https://dibbs2.bsm.dla.mil/Downloads/RFQ/Archive/ca210731.zip")
driver.find_element_by_id("butAgree").click()
Here we are setting some profiles to disable pop out, download dialog.
It is working perfectly fine in latest version of Firefox and 3.141.0 version of selenium

Autodownload for firefox in selenium using python [duplicate]

My purpose it to download a zip file from https://www.shareinvestor.com/prices/price_download_zip_file.zip?type=history_all&market=bursa
It is a link in this webpage https://www.shareinvestor.com/prices/price_download.html#/?type=price_download_all_stocks_bursa. Then save it into this directory "/home/vinvin/shKLSE/ (I am using pythonaywhere). Then unzip it and the csv file extract in the directory.
The code run until the end with no error but it does not downloaded.
The zip file is automatically downloaded when click on https://www.shareinvestor.com/prices/price_download_zip_file.zip?type=history_all&market=bursa manually.
My code with a working username and password is used. The real username and password is used so that it is easier to understand the problem.
#!/usr/bin/python
print "hello from python 2"
import urllib2
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import time
from pyvirtualdisplay import Display
import requests, zipfile, os
display = Display(visible=0, size=(800, 600))
display.start()
profile = webdriver.FirefoxProfile()
profile.set_preference('browser.download.folderList', 2)
profile.set_preference('browser.download.manager.showWhenStarting', False)
profile.set_preference('browser.download.dir', "/home/vinvin/shKLSE/")
profile.set_preference('browser.helperApps.neverAsk.saveToDisk', '/zip')
for retry in range(5):
try:
browser = webdriver.Firefox(profile)
print "firefox"
break
except:
time.sleep(3)
time.sleep(1)
browser.get("https://www.shareinvestor.com/my")
time.sleep(10)
login_main = browser.find_element_by_xpath("//*[#href='/user/login.html']").click()
print browser.current_url
username = browser.find_element_by_id("sic_login_header_username")
password = browser.find_element_by_id("sic_login_header_password")
print "find id done"
username.send_keys("bkcollection")
password.send_keys("123456")
print "log in done"
login_attempt = browser.find_element_by_xpath("//*[#type='submit']")
login_attempt.submit()
browser.get("https://www.shareinvestor.com/prices/price_download.html#/?type=price_download_all_stocks_bursa")
print browser.current_url
time.sleep(20)
dl = browser.find_element_by_xpath("//*[#href='/prices/price_download_zip_file.zip?type=history_all&market=bursa']").click()
time.sleep(30)
browser.close()
browser.quit()
display.stop()
zip_ref = zipfile.ZipFile(/home/vinvin/sh/KLSE, 'r')
zip_ref.extractall(/home/vinvin/sh/KLSE)
zip_ref.close()
os.remove(zip_ref)
HTML snippet:
<li>All Historical Data <span>About 220 MB</span></li>
Note that &amp is shown when I copy the snippet. It was hidden from view source, so I guess it is written in JavaScript.
Observation I found
The directory home/vinvin/shKLSE do not created even I run the code with no error
I try to download a much smaller zip file which can be completed in a second but still do not download after a wait of 30s. dl = browser.find_element_by_xpath("//*[#href='/prices/price_download_zip_file.zip?type=history_daily&date=20170519&market=bursa']").click()

I don't see any major drawback in your code block as such. But here are a few recommendations through this Solution & the execution of this Automated Test Script:
This code works perfect in Off Market Hours. During Market Hours a lot of JavaScript & Ajax Calls are in play and handling those are beyond the scope of this Question.
You may consider checking for the the intended download directory first & if not available, create a new one. That code block for this functionality is in Windows style and works perfect on Windows platform.
Once you click on "Login" induce some wait for the HTML DOM to render properly.
When you want to see off the downloading process, you need to set certain more preferences in the FirefoxProfile as mentioned in my code below.
Always consider maximizing the browser window through browser.maximize_window()
When you start downloading you need to wait for sufficient amount of time to get the file completely downloaded.
If you are using browser.quit() at the end you don't need to use browser.close()
You may consider to replace all the time.sleep() with either of ImplicitlyWait or ExplicitWait or FluentWait.
Here is your own code block with some simple tweaks in it:
#!/usr/bin/python
print "hello from python 2"
import urllib2
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import time
from pyvirtualdisplay import Display
import requests, zipfile, os
display = Display(visible=0, size=(800, 600))
display.start()
newpath = 'C:\\home\\vivvin\\shKLSE'
if not os.path.exists(newpath):
os.makedirs(newpath)
profile = webdriver.FirefoxProfile()
profile.set_preference("browser.download.dir",newpath);
profile.set_preference("browser.download.folderList",2);
profile.set_preference("browser.helperApps.neverAsk.saveToDisk", "application/zip");
profile.set_preference("browser.download.manager.showWhenStarting",False);
profile.set_preference("browser.helperApps.neverAsk.openFile","application/zip");
profile.set_preference("browser.helperApps.alwaysAsk.force", False);
profile.set_preference("browser.download.manager.useWindow", False);
profile.set_preference("browser.download.manager.focusWhenStarting", False);
profile.set_preference("browser.helperApps.neverAsk.openFile", "");
profile.set_preference("browser.download.manager.alertOnEXEOpen", False);
profile.set_preference("browser.download.manager.showAlertOnComplete", False);
profile.set_preference("browser.download.manager.closeWhenDone", True);
profile.set_preference("pdfjs.disabled", True);
for retry in range(5):
try:
browser = webdriver.Firefox(profile)
print "firefox"
break
except:
time.sleep(3)
time.sleep(1)
browser.maximize_window()
browser.get("https://www.shareinvestor.com/my")
time.sleep(10)
login_main = browser.find_element_by_xpath("//*[#href='/user/login.html']").click()
time.sleep(10)
print browser.current_url
username = browser.find_element_by_id("sic_login_header_username")
password = browser.find_element_by_id("sic_login_header_password")
print "find id done"
username.send_keys("bkcollection")
password.send_keys("123456")
print "log in done"
login_attempt = browser.find_element_by_xpath("//*[#type='submit']")
login_attempt.submit()
browser.get("https://www.shareinvestor.com/prices/price_download.html#/?type=price_download_all_stocks_bursa")
print browser.current_url
time.sleep(20)
dl = browser.find_element_by_xpath("//*[#href='/prices/price_download_zip_file.zip?type=history_all&market=bursa']").click()
time.sleep(900)
browser.close()
browser.quit()
display.stop()
zip_ref = zipfile.ZipFile(/home/vinvin/sh/KLSE, 'r')
zip_ref.extractall(/home/vinvin/sh/KLSE)
zip_ref.close()
os.remove(zip_ref)
Let me know if this Answers your Question.

I rewrote your script, with comments explaining why I made the changes I made. I think your main problem might have been a bad mimetype, however, your script had a log of systemic issues that would have made it unreliable at best. This rewrite uses explicit waits, which completely removes the need to use time.sleep(), allowing it to run as fast as possible, while also eliminating errors that arise from network congestion.
You will need do the following to make sure all modules are installed:
pip install requests explicit selenium retry pyvirtualdisplay
The script:
#!/usr/bin/python
from __future__ import print_function # Makes your code portable
import os
import glob
import zipfile
from contextlib import contextmanager
import requests
from retry import retry
from explicit import waiter, XPATH, ID
from selenium import webdriver
from pyvirtualdisplay import Display
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.wait import WebDriverWait
DOWNLOAD_DIR = "/tmp/shKLSE/"
def build_profile():
profile = webdriver.FirefoxProfile()
profile.set_preference('browser.download.folderList', 2)
profile.set_preference('browser.download.manager.showWhenStarting', False)
profile.set_preference('browser.download.dir', DOWNLOAD_DIR)
# I think your `/zip` mime type was incorrect. This works for me
profile.set_preference('browser.helperApps.neverAsk.saveToDisk',
'application/vnd.ms-excel,application/zip')
return profile
# Retry is an elegant way to retry the browser creation
# Though you should narrow the scope to whatever the actual exception is you are
# retrying on
#retry(Exception, tries=5, delay=3)
#contextmanager # This turns get_browser into a context manager
def get_browser():
# Use a context manager with Display, so it will be closed even if an
# exception is thrown
profile = build_profile()
with Display(visible=0, size=(800, 600)):
browser = webdriver.Firefox(profile)
print("firefox")
try:
yield browser
finally:
# Let a try/finally block manage closing the browser, even if an
# exception is called
browser.quit()
def main():
print("hello from python 2")
with get_browser() as browser:
browser.get("https://www.shareinvestor.com/my")
# Click the login button
# waiter is a helper function that makes it easy to use explicit waits
# with it you dont need to use time.sleep() calls at all
login_xpath = '//*/div[#class="sic_logIn-bg"]/a'
waiter.find_element(browser, login_xpath, XPATH).click()
print(browser.current_url)
# Log in
username = "bkcollection"
username_id = "sic_login_header_username"
password = "123456"
password_id = "sic_login_header_password"
waiter.find_write(browser, username_id, username, by=ID)
waiter.find_write(browser, password_id, password, by=ID, send_enter=True)
# Wait for login process to finish by locating an element only found
# after logging in, like the Logged In Nav
nav_id = 'sic_loggedInNav'
waiter.find_element(browser, nav_id, ID)
print("log in done")
# Load the target page
target_url = ("https://www.shareinvestor.com/prices/price_download.html#/?"
"type=price_download_all_stocks_bursa")
browser.get(target_url)
print(browser.current_url)
# CLick download button
all_data_xpath = ("//*[#href='/prices/price_download_zip_file.zip?"
"type=history_all&market=bursa']")
waiter.find_element(browser, all_data_xpath, XPATH).click()
# This is a bit challenging: You need to wait until the download is complete
# This file is 220 MB, it takes a while to complete. This method waits until
# there is at least one file in the dir, then waits until there are no
# filenames that end in `.part`
# Note that is is problematic if there is already a file in the target dir. I
# suggest looking into using the tempdir module to create a unique, temporary
# directory for downloading every time you run your script
print("Waiting for download to complete")
at_least_1 = lambda x: len(x("{0}/*.zip*".format(DOWNLOAD_DIR))) > 0
WebDriverWait(glob.glob, 300).until(at_least_1)
no_parts = lambda x: len(x("{0}/*.part".format(DOWNLOAD_DIR))) == 0
WebDriverWait(glob.glob, 300).until(no_parts)
print("Download Done")
# Now do whatever it is you need to do with the zip file
# zip_ref = zipfile.ZipFile(DOWNLOAD_DIR, 'r')
# zip_ref.extractall(DOWNLOAD_DIR)
# zip_ref.close()
# os.remove(zip_ref)
print("Done!")
if __name__ == "__main__":
main()
Full disclosure: I maintain the explicit module. It is designed to make using explicit waits much easier, for exactly situations like this, where websites slowly load in dynamic content based on user interactions. You could replace all of the waiter.XXX calls above with direct explicit waits.

Take it out side the scope of the selenium. Change the preference settings so that when the link is clicked (First check if link is valid) it gives you a pop up asking to save , now use sikuli http://www.sikuli.org/ to click on the popup.
Mime types does not always work, and there is no black and white answer why it is not working.

The reason is due to the webpage is loading slowly. I added a wait of 20 seconds after open the webpage link
login_attempt.submit()
browser.get("https://www.shareinvestor.com/prices/price_download.html#/?type=price_download_all_stocks_bursa")
print browser.current_url
time.sleep(20)
dl = browser.find_element_by_xpath("//*[#href='/prices/price_download_zip_file.zip?type=history_all&market=bursa']").click()
It returns no error.
Additional,
/zip is incorrect MIME type. Change to profile.set_preference('browser.helperApps.neverAsk.saveToDisk', 'application/zip')
The final correction :
#!/usr/bin/python
print "hello from python 2"
import urllib2
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import time
from pyvirtualdisplay import Display
import requests, zipfile, os
display = Display(visible=0, size=(800, 600))
display.start()
profile = webdriver.FirefoxProfile()
profile.set_preference('browser.download.folderList', 2)
profile.set_preference('browser.download.manager.showWhenStarting', False)
profile.set_preference('browser.download.dir', "/home/vinvin/shKLSE/")
# application/zip not /zip
profile.set_preference('browser.helperApps.neverAsk.saveToDisk', 'application/zip')
for retry in range(5):
try:
browser = webdriver.Firefox(profile)
print "firefox"
break
except:
time.sleep(3)
time.sleep(1)
browser.get("https://www.shareinvestor.com/my")
time.sleep(10)
login_main = browser.find_element_by_xpath("//*[#href='/user/login.html']").click()
print browser.current_url
username = browser.find_element_by_id("sic_login_header_username")
password = browser.find_element_by_id("sic_login_header_password")
print "find id done"
username.send_keys("bkcollection")
password.send_keys("123456")
print "log in done"
login_attempt = browser.find_element_by_xpath("//*[#type='submit']")
login_attempt.submit()
browser.get("https://www.shareinvestor.com/prices/price_download.html#/?type=price_download_all_stocks_bursa")
print browser.current_url
time.sleep(20)
dl = browser.find_element_by_xpath("//*[#href='/prices/price_download_zip_file.zip?type=history_all&market=bursa']").click()
time.sleep(30)
browser.close()
browser.quit()
display.stop()
zip_ref = zipfile.ZipFile('/home/vinvin/shKLSE/file.zip', 'r')
zip_ref.extractall('/home/vinvin/shKLSE')
zip_ref.close()
# remove with correct path
os.remove('/home/vinvin/shKLSE/file.zip')

I haven't tried on the site you mentioned, however following code works perfectly and downloads the ZIP. if you are not able to download the zip, Mime type could be different. you can use chrome browser and network inspection to check the mime type of the file you are trying to download.
profile = webdriver.FirefoxProfile()
profile.set_preference('browser.download.folderList', 2)
profile.set_preference('browser.download.manager.showWhenStarting', False)
profile.set_preference('browser.download.dir', "/home/vinvin/shKLSE/")
profile.set_preference('browser.helperApps.neverAsk.saveToDisk', 'application/zip')
browser = webdriver.Firefox(profile)
browser.get("http://www.colorado.edu/conflict/peace/download/peace.zip")

Loop through downloading files using selenium in Python

This is a follow-up question to this previous question on how to download ~1000 files from Google Patents.
I would like to iterate through a list of filenames fname = ["ipg150106.zip", "ipg150113.zip"] and simulate clicking and saving these files to my computer. The following example works for me and downloads a single file:
from selenium import webdriver
from selenium.webdriver.firefox.firefox_profile import FirefoxProfile
# Define parameters
savepath = 'D:\\' # set the desired path here for the files
# Download the files from Google Patents
profile = FirefoxProfile ()
profile.set_preference("browser.download.panel.shown", False)
profile.set_preference("browser.download.folderList", 2) # 2 means specify custom location
profile.set_preference("browser.download.manager.showWhenStarting", False)
profile.set_preference("browser.download.dir", savepath) # choose folder to download to
profile.set_preference("browser.helperApps.neverAsk.saveToDisk",'application/octet-stream')
driver = webdriver.Firefox(firefox_profile=profile)
url = 'https://www.google.com/googlebooks/uspto-patents-grants-text.html#2015'
driver.get(url)
filename = driver.find_element_by_xpath('//a[contains(text(), "ipg150106.zip")]')
filename.click()
I've tried to replace this with a list and a loop like this:
fname = ["ipg150106.zip", "ipg150113.zip"]
for f in fname:
filename = driver.find_element_by_xpath('//a[contains(text(), f)]')
filename.click()
print('Finished loop for: {}.'.format(f))
However, the browser opens, but nothing happens (no clicking on files). Any ideas?

You need to pass the filename into the XPath expression:
filename = driver.find_element_by_xpath('//a[contains(text(), "{filename}")]'.format(filename=f))
Though, an easier location technique here would be "by partial link text":
for f in fname:
filename = driver.find_element_by_partial_link_text(f)
filename.click()

How to emulate Firefox "Save File" -> OK in Python

My following code:
#!/usr/bin/env python
from selenium import webdriver
from selenium.webdriver.support.ui import Select
from selenium.webdriver.common.by import By
# Define firefox profile
download_dir = "/Users/pdubois/Desktop/TargetMine_Output/"
fp = webdriver.FirefoxProfile()
fp.set_preference("browser.download.folderList",2)
fp.set_preference("browser.download.manager.showWhenStarting",False)
fp.set_preference("browser.download.dir", download_dir)
#fp.set_preference("browser.helperApps.neverAsk.saveToDisk", "text")
fp.set_preference("browser.helperApps.neverAsk.saveToDisk", "text/plain")
driver = webdriver.Firefox(fp)
driver.implicitly_wait(20)
genes = "Eif2ak2,Pcgf5,Vps25,Prmt6,Tcerg1,Dnttip2,Preb,Polr1b,Gabpb1,Prdm1,Fosl2,Zfp143,Psip1,Kat6a,Tgif1,Txn1,Irf8,Cnot6l,Zfp451,Foxk2,Lpxn,Etv6,Khsrp,Lmo4,Nkrf,Mafk,Mbd1,Cited2,Elp5,Jdp2,Bzw1,Rbm15b,Klf9,Gtf2e2,Dynll1,Klf6,Stat1,Srrt,Gtf2f1,Adnp2,Ikbkg,Mybbp1a,Nup62,Brd2,Chd1,Kctd1,Sap30,Cebpd,Mtf1,Gtf2h2,Fubp1,Tcea1,Irf2bp2,Ezh2,Hnrpdl,Pml,Cebpz,Med7"
targetmine_url = "http://targetmine.nibio.go.jp/targetmine/begin.do"
driver.get(targetmine_url)
# Define type of list to be submitted
gene_select = Select(driver.find_element_by_name("type"))
gene_select.select_by_visible_text(u"Gene")
# Enter list and submit
gene_input = driver.find_element_by_id("listInput")
gene_input.send_keys(genes)
submit = driver.find_element_by_css_selector("input.button.light").click()
# Choose name for list
driver.find_element_by_id("newBagName").clear()
driver.find_element_by_id("newBagName").send_keys("ADX.06.ID.Clust1")
driver.switch_to_frame("__pomme::0")
# Add All
driver.find_element_by_css_selector("span.small.success.add-all.button").click()
# Save all genes
driver.find_element_by_css_selector("a.success.button.save").click()
# Select M. Musculus
driver.find_element_by_xpath("//ul[#id='customConverter']/li[2]/a[1]").click()
# Gene enrchment part
go_xpath = "//div[#id='gene_go_enrichment-widget']/div[#class='inner']/div[1]/div[#class='form']/form[#style='margin:0']/div[2]/select[1]"
#driver.find_element_by_xpath(go_xpath).click()
go_select = Select(driver.find_element_by_xpath(go_xpath))
go_select.select_by_visible_text(u"1.00")
# Download
#driver.find_element_by_css_selector("a.btn.btn-small.export").click()
Works fine. Which end with this instances:
One last thing I want to achieve then is to Save the file automatically.
Despite I've already set the Firefox profile at the top
of the code, it doesn't do as I hoped. What's the right way to do it?
Update:
The solution by alecxe works.
Except I tried this, it doesn't save the file.
go_download_xpath = "//div[#id='gene_go_enrichment-widget']/div[#class='inner']/div[1]/div[2]/a[#class='btn btn-small export']"
driver.find_element_by_xpath(go_download_xpath).click()
# it saved the specific desired file.
# using
#driver.find_element_by_css_selector("a.btn.btn-small.export").click()
#save the wrong file.

This particular dialog cannot be controlled via selenium - this is a browser popup, not a javascript popup (which can be automated with swith_to.alert).
In this case, you need to avoid the popup being shown in the first place and make Firefox download the file automatically by tweaking browser's desired capabilities (aka profile preferences). Firefox can download files automatically depending on the mime-type of the file being downloaded. In your case it is text/plain:
fp = webdriver.FirefoxProfile()
fp.set_preference("browser.download.folderList",2)
fp.set_preference("browser.download.dir", download_dir)
fp.set_preference("browser.download.manager.showWhenStarting", False)
fp.set_preference("browser.helperApps.neverAsk.saveToDisk", "text/plain")
driver = webdriver.Firefox(firefox_profile=fp)
FYI, I've downloaded the file manually and used magic module to detect the mime-type:
In [1]: import magic
In [2]: mime = magic.Magic(mime=True)
In [3]: mime.from_file("result.tsv")
Out[3]: 'text/plain'

Try:
fp = webdriver.FirefoxProfile()
fp.set_preference("browser.download.dir", download_dir)
fp.set_preference("browser.preferences.instantApply", True)
fp.set_preference("browser.helperApps.neverAsk.saveToDisk",
"text/plain, application/octet-stream, application/binary, text/csv, application/csv, application/excel, text/comma-separated-values, text/xml, application/xml")
fp.set_preference("browser.helperApps.alwaysAsk.force", False)
fp.set_preference("browser.download.manager.showWhenStarting", False)
fp.set_preference("browser.download.folderList", 2)
driver = webdriver.Firefox(firefox_profile=fp)