{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Dynamically loaded content downloader"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Selenium + BeautifulSoup "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "https://dvenkatsagar.github.io/tutorials/python/2015/10/26/ddlv/"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "# The standard library modules\n",
    "import os\n",
    "import sys\n",
    "\n",
    "# The wget module\n",
    "import wget\n",
    "\n",
    "# The BeautifulSoup module\n",
    "from bs4 import BeautifulSoup\n",
    "\n",
    "# The selenium module\n",
    "from selenium import webdriver\n",
    "from selenium.webdriver.common.keys import Keys\n",
    "from selenium.webdriver.support.ui import WebDriverWait\n",
    "from selenium.webdriver.support import expected_conditions as EC\n",
    "from selenium.webdriver.common.by import By"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "driver = webdriver.Firefox(\"/Users/pnofrc/\")\n",
    "#driver = webdriver.Chrome(\"/Users/pnofrc/\")\n",
    "driver.get(\"https://mubi.com/it/films/music-and-apocalypse/watch\") # load the web page"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# for websites that need you to login to access the information\n",
    "elem = driver.find_element_by_id(\"email\") # Find the email input field of the login form\n",
    "elem.send_keys(\"user@example.com\") # Send the users email\n",
    "elem = driver.find_element_by_id(\"pwd\") # Find the password field of the login form\n",
    "elem.send_keys(\"userpwd\") # send the users password\n",
    "elem.send_keys(Keys.RETURN) # press the enter key"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "driver.get(\"http://www.example.com/path/of/video/page.html\") # load the page that has the video"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "WebDriverWait(driver, 50).until(EC.visibility_of_element_located((By.ID, \"the-element-id\"))) # waits till the element with the specific id appears\n",
    "src = driver.page_source # gets the html source of the page"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "parser = BeautifulSoup(src,\"lxml\") # initialize the parser and parse the source \"src\"\n",
    "list_of_attributes = {\"class\" : \"some-class\", \"name\" : \"some-name\"} # A list of attributes that you want to check in a tag\n",
    "tag = parser.findAll('video',attrs=list_of_attributes) # Get the video tag from the source"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "n = 0 # Specify the index of video element in the web page\n",
    "url = tag[n]['src'] # get the src attribute of the video\n",
    "wget.download(url,out=\"path/to/output/file\") # download the video"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "driver.close() # closes the driver"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}