fixed: code

Author: afunTW

practice/09_crawling_reCAPTCHA_image.ipynb

@@ -13,7 +13,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 1,
    "metadata": {
     "collapsed": true
    },
@@ -22,12 +22,11 @@
     "import os\n",
     "import hashlib\n",
     "import requests\n",
+    "import time\n",
     "\n",
     "from selenium import webdriver\n",
     "from selenium.webdriver.common.keys import Keys\n",
     "from selenium.webdriver.common.by import By\n",
-    "from selenium.webdriver.support.ui import WebDriverWait\n",
-    "from selenium.webdriver.support import expected_conditions as EC\n",
     "\n",
     "from fake_useragent import UserAgent\n",
     "from PIL import Image\n",
@@ -38,41 +37,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "class ReloadImage(object):\n",
-    "    def __init__(self, locator, xpath, compare):\n",
-    "        self.locator = locator\n",
-    "        self.xpath = xpath\n",
-    "        self.compare = compare\n",
-    "    def __call__(self, driver):\n",
-    "        element = driver.find_element(self.locator, self.xpath)\n",
-    "        attr = element.get_attribute('src')\n",
-    "        if attr != self.compare:\n",
-    "            return element\n",
-    "        else:\n",
-    "            return False"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Save img - /home/dirl/github/Python-Crawling-Tutorial/results/dcc521eea7e48f005685d58e770fc9be.JPEG\n",
-      "click\n",
-      "Save img - /home/dirl/github/Python-Crawling-Tutorial/results/6cf5653979671789ef664c9122f83f6f.JPEG\n",
-      "click\n",
-      "Message: chrome not reachable\n",
-      "  (Session info: chrome=64.0.3282.119)\n",
-      "  (Driver info: chromedriver=2.35.528139 (47ead77cb35ad2a9a83248b292151462a66cd881),platform=Linux 4.13.0-26-generic x86_64)\n",
-      "\n"
+      "Save img - /home/dirl/github/Python-Crawling-Tutorial/results/ceecac6a5a9677750a69c80a87f26080.JPEG\n",
+      "Save img - /home/dirl/github/Python-Crawling-Tutorial/results/ceecac6a5a9677750a69c80a87f26080.JPEG\n",
+      "Save img - /home/dirl/github/Python-Crawling-Tutorial/results/4cce70c2cdde67af52e27920693da213.JPEG\n",
+      "Save img - /home/dirl/github/Python-Crawling-Tutorial/results/1682c3490f1ec9df1da4a43407f890b7.JPEG\n",
+      "Save img - /home/dirl/github/Python-Crawling-Tutorial/results/aa6a4d1bfa181fc53636a341562fb2ea.PNG\n"
      ]
     }
    ],
@@ -85,13 +61,12 @@
     "    driver = webdriver.Chrome()\n",
     "    driver.get(url)\n",
     "    driver.maximize_window()\n",
-    "    wait = WebDriverWait(driver, 10)\n",
+    "    driver.implicitly_wait(10)\n",
     "    compare_url = ''\n",
     "    \n",
     "    for i in range(5):\n",
     "        # get image\n",
-    "        #img_el = driver.find_element(By.XPATH, '//div[@id=\"recaptcha_image\"]/img')\n",
-    "        img_el = wait.until(ReloadImage(By.XPATH, '//div[@id=\"recaptcha_image\"]/img', compare_url))\n",
+    "        img_el = driver.find_element(By.XPATH, '//div[@id=\"recaptcha_image\"]/img')\n",
     "        img_url = img_el.get_attribute('src')\n",
     "        img_filename = hashlib.md5(img_url.encode('utf-8')).hexdigest()\n",
     "        compare_url = img_url\n",
@@ -106,7 +81,7 @@
     "        \n",
     "        # re-generate image\n",
     "        btn_refresh = driver.find_element(By.XPATH, '//*[@id=\"recaptcha_reload_btn\"]').click()\n",
-    "        print('click')\n",
+    "        time.sleep(2)\n",
     "        \n",
     "\n",
     "except Exception as e:\n",