Welcome!
This is the community forum for my apps Pythonista and Editorial.
For individual support questions, you can also send an email. If you have a very short question or just want to say hello — I'm @olemoritz on Twitter.
How to login Facebook with Request module for further access?
-
Hi All, with the help of some nice guys here, I finished my first pythonista little project, a facebook video downloader: https://gist.github.com/henryaukc/6fd00b8baee4c069a2b44e574829469f
It works for downloading videos posted by the pages that open to public access. I would like to enhance it a bit so that it can download videos from my friends page. It requires to login the facebook with my credentials and save the cookies to further access the pages. I have searched the web for solutions but it seems all outdated and see if someone can give me some hints?
I will continue to investigate it and post my result here too. Thanks a lot.
-
The selected answer from the following stackoverflow link may help
http://stackoverflow.com/questions/12737740/python-requests-and-persistent-sessions -
Thanks @abcabc ! I have tried the script and it works fine after some small modification. I would try to update my script accordingly later.
-
Sorry, maybe I was not checking thoroughly or it is not working anymore, my script to login facebook fails now....
Can someone shed some light on it?
import requests from urllib.parse import urlparse import os import pickle import datetime class MyLoginSession: """ a class which handles and saves login sessions. It also keeps track of proxy settings. It does also maintine a cache-file for restoring session data from earlier script executions. """ def __init__(self, loginUrl, loginData, loginTestUrl, loginTestString, sessionFileAppendix = '_session.dat', maxSessionTimeSeconds = 30 * 60, proxies = None, userAgent = 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:40.0) Gecko/20100101 Firefox/40.1', debug = True): """ save some information needed to login the session you'll have to provide 'loginTestString' which will be looked for in the responses html to make sure, you've properly been logged in 'proxies' is of format { 'https' : 'https://user:pass@server:port', 'http' : ... 'loginData' will be sent as post data (dictionary of id : value). 'maxSessionTimeSeconds' will be used to determine when to re-login. """ urlData = urlparse(loginUrl) self.proxies = proxies self.loginData = loginData self.loginUrl = loginUrl self.loginTestUrl = loginTestUrl self.maxSessionTime = maxSessionTimeSeconds self.sessionFile = urlData.netloc + sessionFileAppendix self.userAgent = userAgent self.loginTestString = loginTestString self.debug = debug self.login() def modification_date(self, filename): """ return last file modification date as datetime object """ t = os.path.getmtime(filename) return datetime.datetime.fromtimestamp(t) def login(self, forceLogin = False): """ login to a session. Try to read last saved session from cache file. If this fails do proper login. If the last cache access was too old, also perform a proper login. Always updates session cache file. """ wasReadFromCache = False if self.debug: print('loading or generating session...') if os.path.exists(self.sessionFile) and not forceLogin: if os.path.getsize(self.sessionFile) > 0: time = self.modification_date(self.sessionFile) if self.debug: print('loginURL:' + loginUrl) # only load if file less than 30 minutes old lastModification = (datetime.datetime.now() - time).seconds if lastModification < self.maxSessionTime: with open(self.sessionFile, "rb") as f: self.session = pickle.load(f) wasReadFromCache = True if self.debug: print("loaded session from cache (last access %ds ago) " % lastModification) if not wasReadFromCache: self.session = requests.Session() self.session.headers.update({'user-agent' : self.userAgent}) res = self.session.post(self.loginUrl, data = self.loginData, proxies = self.proxies) if self.debug: print('created new session with login' ) self.saveSessionToCache() # test login res = self.session.get(self.loginTestUrl) if res.text.find(self.loginTestString) > 0: print(res.text) raise Exception("could not log into provided site '%s'" " (did not find successful login string)" % self.loginUrl) def saveSessionToCache(self): """ save session to a cache file """ # always save (to update timeout) with open(self.sessionFile, "wb") as f: pickle.dump(self.session, f) if self.debug: print('updated session cache-file %s' % self.sessionFile) def retrieveContent(self, url, method = "get", postData = None): """ return the content of the url with respect to the session. If 'method' is not 'get', the url will be called with 'postData' as a post request. """ if method == 'get': res = self.session.get(url , proxies = self.proxies) else: res = self.session.get(url , data = postData, proxies = self.proxies) res.encoding = 'utf-8' # the session has been updated on the server, so also update in cache self.saveSessionToCache() return res if __name__ == "__main__": # proxies = {'https' : 'https://user:pass@server:port', # 'http' : 'http://user:pass@server:port'} # after I checking the source code of Facebook login form, I changed 'user' to 'email' and it also failed loginData = { 'user' : 'My Login Name', 'password' : 'My Password'} # these are not my real login & password loginUrl = 'https://www.facebook.com/login.php' loginTestUrl = 'https://www.facebook.com/home.php?ref=home' failedStr = 'facebook.com/login/' s = MyLoginSession(loginUrl, loginData, loginTestUrl, failedStr, #proxies = proxies ) res = s.retrieveContent('https://www.facebook.com/home.php?ref=home') res.encoding = 'utf-8' print(res.text) ''' <input type="text" class="inputtext _55r1 inputtext _1kbt inputtext _1kbt" name="email" id="email" tabindex="1" placeholder="Email address or phone number" value="" autofocus="1" aria-label="Email address or phone number"> </div> <div class="clearfix _5466 _44mg"> <input type="password" class="inputtext _55r1 inputtext _1kbt inputtext _1kbt" name="pass" id="pass" tabindex="1" placeholder="Password" aria-label="Password"> '''```