How to scrape a website that requires login first with Python

Question

First of all, I think it's worth saying that, I know there are a bunch of similar questions but NONE of them works for me...

I'm a newbie on Python, html and web scraper. I'm trying to scrape user information from a website which needs to login first. In my tests I use scraper my email settings from github as examples. The main page is 'https://github.com/login' and the target page is 'https://github.com/settings/emails'

Here are a list of methods I've tried

##################################### Method 1
import mechanize
import cookielib
from BeautifulSoup import BeautifulSoup
import html2text

br = mechanize.Browser()
cj = cookielib.LWPCookieJar()
br.set_cookiejar(cj)

# Browser options
br.set_handle_equiv(True)
br.set_handle_gzip(True)
br.set_handle_redirect(True)
br.set_handle_referer(True)
br.set_handle_robots(False)
br.set_handle_refresh(mechanize._http.HTTPRefreshProcessor(), max_time=1)


br.addheaders = [('User-agent', 'Chrome')]

# The site we will navigate into, handling it's session
br.open('https://github.com/login')

for f in br.forms():
    print f

br.select_form(nr=0)

# User credentials
br.form['login'] = 'myusername'
br.form['password'] = 'mypwd'

# Login
br.submit()

br.open('github.com/settings/emails').read()


################ Method 2
import urllib, urllib2, cookielib

username = 'myusername'
password = 'mypwd'

cj = cookielib.CookieJar()
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
login_data = urllib.urlencode({'username' : username, 'j_password' : password})
opener.open('https://github.com/login', login_data)
resp = opener.open('https://github.com/settings/emails')
print resp.read()



############# Method 3
import urllib
opener = urllib.FancyURLopener()
print opener.open('http://myusername:[email protected]/settings/emails').read()




########## Method 4
import mechanize
import cookielib

br = mechanize.Browser()
cj = cookielib.LWPCookieJar()
br.set_cookiejar(cj)

br.set_handle_equiv(True)
br.set_handle_gzip(True)
br.set_handle_redirect(True)
br.set_handle_referer(True)
br.set_handle_robots(False)
br.set_handle_refresh(mechanize._http.HTTPRefreshProcessor(), max_time=1)
#br.set_debug_http(True)
#br.set_debug_redirects(True)
#br.set_debug_responses(True)

br.addheaders = [('User-agent', 'Chrome')]

br.add_password('https://github.com/settings/emails', 'myusername', 'mypwd')
br.open('https://github.com/settings/emails')
print br.response().read()



############ Methods 5
from requests import session

payload = {
    'action': 'login',
    'username': 'myusername',
    'password': 'mypwd'
}

with session() as c:
    c.post('https://github.com/login', data=payload)
    request = c.get('https://github.com/settings/emails')
    print request.headers
    print request.text



########### Method 6
import requests
from requests.packages.urllib3 import add_stderr_logger
import sys
from bs4 import BeautifulSoup as bs

add_stderr_logger()
s = requests.Session()

s.headers['User-Agent'] = 'Chrome'

username = 'myusername'
password = 'mypwd'
url = 'https://github.com/login'

# after examining the HTML of the website you're trying to log into
# set name_form to the name of the form element that contains the name and
# set password_form to the name of the form element that will contain the password
login = {'login': username, 'password': password}
login_response = s.post(url, data=login)
for r in login_response.history:
    if r.status_code == 401:  # 401 means authentication failed
        print 'error!'
        sys.exit(1)  # abort


pdf_response = s.get('https://github.com/settings/emails')  # Your cookies and headers are automatically included
soup = bs(pdf_response.content)

Also I've read some discussions about differences between HTTP Authentication and cookies. Still none of them worked.

Please help and any help would be appreciated. Thank you very much.

Answer 1

This works for me:

##################################### Method 1
import mechanize
import cookielib
from BeautifulSoup import BeautifulSoup
import html2text

# Browser
br = mechanize.Browser()

# Cookie Jar
cj = cookielib.LWPCookieJar()
br.set_cookiejar(cj)

# Browser options
br.set_handle_equiv(True)
br.set_handle_gzip(True)
br.set_handle_redirect(True)
br.set_handle_referer(True)
br.set_handle_robots(False)
br.set_handle_refresh(mechanize._http.HTTPRefreshProcessor(), max_time=1)

br.addheaders = [('User-agent', 'Chrome')]

# The site we will navigate into, handling it's session
br.open('https://github.com/login')

# View available forms
for f in br.forms():
    print f

# Select the second (index one) form (the first form is a search query box)
br.select_form(nr=1)

# User credentials
br.form['login'] = 'mylogin'
br.form['password'] = 'mypass'

# Login
br.submit()

print(br.open('https://github.com/settings/emails').read())

You were not far off at all!