starting to download VAERS data

.gitignore

@@ -10,3 +10,4 @@ src/results/
 docs/data/*.xlsx
 docs/data/*.html
 .env
+src/captchaImage.jpeg

src/HowBadIsMyBatch.ipynb

@@ -80,10 +80,37 @@
   },
   {
    "cell_type": "markdown",
-   "id": "f3f94f5a",
+   "id": "9514f5be",
    "metadata": {},
    "source": [
-    "## Solve CAPTCHA"
+    "## Download VAERS-Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "777ff543",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from selenium import webdriver\n",
+    "from webdriver_manager.chrome import ChromeDriverManager\n",
+    "from selenium.webdriver.chrome.service import Service as ChromeService\n",
+    "from selenium.webdriver.chrome.options import Options\n",
+    "from selenium.webdriver.common.by import By\n",
+    "\n",
+    "options = Options()\n",
+    "downloadDir = \"/home/frankknoll/Dokumente/Corona/projects/HowBadIsMyBatch/src/VAERS/tmp\"\n",
+    "prefs = {\"download.default_directory\" : downloadDir}\n",
+    "options.add_experimental_option(\"prefs\", prefs)\n",
+    "service = ChromeService(executable_path = ChromeDriverManager().install())\n",
+    "driver = webdriver.Chrome(service = service, options = options)\n",
+    "file2Download = '2022VAERSData.zip'\n",
+    "driver.get('https://vaers.hhs.gov/eSubDownload/index.jsp?fn=' + file2Download)\n",
+    "captchaImage = driver.find_element(By.CSS_SELECTOR, \"img[src='captchaImage']\")\n",
+    "captchaImageFile = 'captchaImage.jpeg'\n",
+    "with open(captchaImageFile, 'wb') as file:\n",
+    "    file.write(captchaImage.screenshot_as_png)"
    ]
   },
   {
@@ -135,10 +162,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "textByImage = {}\n",
+    "textInImage = detectTextInImage(captchaImageFile)"
-    "for i in range(1, 2):\n",
-    "    captchaImage = \"captchaImage\" + str(i) + \".jpeg\"\n",
-    "    textByImage[captchaImage] = detectTextInImage(\"/home/frankknoll/Dokumente/Corona/CAPTCHA/images/VAERS/\" + captchaImage)"
    ]
   },
   {
@@ -154,11 +178,81 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "6ba0ad8e",
+   "id": "2dfc95c3",
    "metadata": {},
    "outputs": [],
    "source": [
-    "textByImage"
+    "textInImage"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0bf84d1c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "driver.find_element(By.ID, \"verificationCode\").send_keys(textInImage)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6cf55175",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "driver.find_element(By.CSS_SELECTOR, '[name=\"downloadbut\"]').click()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "86e5056f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def isCaptchaSolved():\n",
+    "    return len(driver.find_elements(By.ID, \"wordverify\")) == 0"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b6b47c06",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import time\n",
+    "import os.path\n",
+    "\n",
+    "def waitUntilDownloadHasFinished():\n",
+    "    while not os.path.exists(downloadDir + \"/\" + file2Download):\n",
+    "        time.sleep(2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b1ebc05c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if isCaptchaSolved():\n",
+    "    waitUntilDownloadHasFinished()\n",
+    "    display('file downloaded')\n",
+    "else:\n",
+    "    display('try again')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "380bcf32",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "driver.quit()"
    ]
   },
   {