Unable to log in to Amazon using Python

I'm using Python 3 to write a script to log in to Amazon to grab my Kindle highlights. It is based on this article: https://blog.jverkamp.com/2015/07/02/scraping-kindle-highlights/

I am unable to successfully log in and instead get a message saying to enable cookies to continue:

<RequestsCookieJar[<Cookie ubid-main=189-4768762-8531647 for .amazon.com/>]>
Failed to login: 

Please Enable Cookies to Continue

To continue shopping at Amazon.com, please enable cookies in your Web browser.
Learn more about cookies and how to enable them.

I have included requests sessions to handle cookies, but it doesn't seem to be working.

Here is the code I am using to try to do this:

import bs4, requests

session = requests.Session()
session.headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.110 Safari/537.36'
}

# Log in to Amazon, we have to get the real login page to bypass CSRF
print('Logging in...')
response = session.get('https://kindle.amazon.com/login')

soup = bs4.BeautifulSoup(response.text, "html.parser")

signin_data = {}
signin_form = soup.find('form', {'name': 'signIn'})
for field in signin_form.find_all('input'):
    try:
        signin_data[field['name']] = field['value']
    except:
        pass

signin_data[u'ap_email'] = 'myemail'
signin_data[u'ap_password'] = 'mypassword'


response = session.post('https://www.amazon.com/ap/signin', data = signin_data)

soup = bs4.BeautifulSoup(response.text, "html.parser")

warning = soup.find('div', {'id': 'message_warning'})
if warning:
    print('Failed to login: {0}'.format(warning.text))

Is there something I'm missing with my use of sessions?

Your signin form data is actually not correct it should be email and password:

signin_data[u'email'] = 'your_email'
signin_data[u'password'] = 'your_password'

You can also avoid the try with a css select and has_attr:

import bs4, requests

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.110 Safari/537.36'
}

from bs4 import BeautifulSoup

with requests.Session() as s:
    s.headers = headers
    r = s.get('https://kindle.amazon.com/login')
    soup = BeautifulSoup(r.content, "html.parser")
    signin_data = {s["name"]: s["value"]
                   for s in soup.select("form[name=signIn]")[0].select("input[name]")
                   if s.has_attr("value")}

    signin_data[u'email'] = 'your_em'
    signin_data[u'password'] = 'pass'

    response = s.post('https://www.amazon.com/ap/signin', data=signin_data)
    soup = bs4.BeautifulSoup(response.text, "html.parser")
    warning = soup.find('div', {'id': 'message_warning'})
    if warning:
        print('Failed to login: {0}'.format(warning.text))
    print(response.content)

The first line of the output, you can see <title>Amazon Kindle: Home</title> at the end:

b'<?xml version="1.0" encoding="utf-8"?>\n<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">\n<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en-US" lang="en-US">\n  <head>\n    <title>Amazon Kindle: Home</title>\n

If it is not working still, you should update your version of requests and maybe try another user-agent. Once I changed the ap_email and ap_password I logged in fine.

来源：https://stackoverflow.com/questions/36488023/unable-to-log-in-to-amazon-using-python

标签

python

amazon

kindle