Update 13_Scraping.ipynb

Author: rsouza

Notebooks/Python_Tasks/13_Scraping.ipynb

@@ -1735,6 +1735,15 @@
     "### 3 - Parsing dynamically updated data via javascript"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "https://stackoverflow.com/questions/8049520/web-scraping-javascript-page-with-python"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 178,
@@ -1777,21 +1786,62 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "import requests\n",
+    "from bs4 import BeautifulSoup\n",
+    "response = requests.get(my_url)\n",
+    "soup = BeautifulSoup(response.text)\n",
+    "soup.find(id=\"intro-text\")\n",
+    "# Result:\n",
+    "<p id=\"intro-text\">No javascript support</p>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from selenium import webdriver\n",
+    "driver = webdriver.PhantomJS()\n",
+    "driver.get(my_url)\n",
+    "p_element = driver.find_element_by_id(id_='intro-text')\n",
+    "print(p_element.text)\n",
+    "# result:\n",
+    "'Yay! Supports javascript'\n"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "from selenium import webdriver\n",
+    "import time\n",
+    "\n",
+    "driver = webdriver.Firefox()\n",
+    "driver.get(url)\n",
+    "time.sleep(5)\n",
+    "htmlSource = driver.page_source"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "import dryscrape\n",
+    "from bs4 import BeautifulSoup\n",
+    "session = dryscrape.Session()\n",
+    "session.visit(my_url)\n",
+    "response = session.body()\n",
+    "soup = BeautifulSoup(response)\n",
+    "soup.find(id=\"intro-text\")\n",
+    "# Result:\n",
+    "<p id=\"intro-text\">Yay! Supports javascript</p>"
+   ]
   },
   {
    "cell_type": "markdown",