addon

dlimg.py

from selenium import webdriver
from selenium.common.exceptions import NoSuchElementException, TimeoutException, StaleElementReferenceException
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.ui import WebDriverWait

import csv
import requests

class FacebookBot(webdriver.Chrome):
    """Main class for browsing facebook"""

    def __init__(self, pathToWebdriver='/usr/local/bin/chromedriver'):
        self.pathToWebdriver = pathToWebdriver
        options = webdriver.ChromeOptions()
        options.add_argument('headless')
        webdriver.Chrome.__init__(self, executable_path=pathToWebdriver, chrome_options=options)
                
    def get(self, url):
        """The make the driver go to the url but reformat the url if is for facebook page"""
        super().get(url)

    def login(self, email, password):
        """Log to facebook using email (str) and password (str)"""

        url = "https://mbasic.facebook.com"
        self.get(url)
        email_element = self.find_element_by_name("email")
        email_element.send_keys(email)
        pass_element = self.find_element_by_name("pass")
        pass_element.send_keys(password)
        pass_element.send_keys(Keys.ENTER)
        """ Bypass facebook OneClick Login """
        if self.find_element_by_class_name("bi"):
            self.find_element_by_class_name("bp").click()
        try:
            self.find_element_by_name("xc_message")
            print("Logged in")
            return True
        except NoSuchElementException as e:
            print("Fail to login",e)
            return False
            
            
def getImage(FacebookBot, postfbid, image_url):
    try:
        FacebookBot.get(image_url)
        realurl = FacebookBot.current_url
        img_data = requests.get(realurl).content
        with open(postfbid + '.jpg', 'wb') as handler:
            handler.write(img_data)
        print ("Saved " + str(realurl))
        return True
    except:
        return False
    
    
def getDirect(imageViewer):
    base = "https://mbasic.facebook.com/photo/view_full_size/?fbid="
    imagefbid = imageViewer.split("=")[1][:-3]
    return (base+imagefbid)
    #return base
    
def scanImage(oneBot, fileHandle):
    for row in csv.reader(fileHandle, delimiter=","):
        postfbid = row[0]
        if row[5] == "" or row[5] == "Multimedia Links":
            continue
        elif len(eval(row[5])) == 1:
            print ("Row 5 " + row[5])
            photourl = getDirect(eval(row[5])[0])
            image = getImage(oneBot, postfbid, photourl)
            print ("Saved 1 item named " + str(postfbid))
        elif len(eval(row[5])) > 1:
            for i in range(len(eval(row[5]))):
                row5list = eval(row[5])
                print ("R5 list")
                print (row5list)
                photourl = getDirect(eval(row[5])[i])
                if i == 0:
                    image = getImage(oneBot, postfbid, photourl)
                image = getImage(oneBot, postfbid + "." + str(i), photourl)
                print ("Saved 1 item in a sequence")
        else:
            print ("Missed 1 item")
        
bot=FacebookBot()
bot.set_page_load_timeout(20)
bot.login("user","pass")
dataFile = open("data.csv", "r")
scanImage(bot, dataFile)


#print (getImage(bot, '1', getDirect("https://mbasic.facebook.com/photo.php?fbid=149612982546044&id=100024920294893&set=gm.2098194463747012&refid=18&__tn__=EH-R")))
#print (getDirect("https://mbasic.facebook.com/photo.php?fbid=149612982546044&id=100024920294893&set=gm.2098194463747012&refid=18&__tn__=EH-R"))