Screenshotting largest diffs

ianmilligan1 · May 7, 2019 · 5cdb174584cd1993d6970a492ba43b22f834129d · 5cdb174
1 parent 3f42756
commit 5cdb174584cd1993d6970a492ba43b22f834129d
diff --git a/NDP_Diffs.ipynb b/NDP_Diffs.ipynb
@@ -128,7 +128,18 @@
  },
  {
   "cell_type": "code",
-  
-   "execution_count": 49,
+  
+   "execution_count": 67,
+  
+   "metadata": {},
+  
+   "outputs": [],
+  
+   "source": [
+  
+    "# let's see the pages with the largest diffs\n",
+  
+    "\n",
+  
+    "sorted = ndp_diffs.sort_values('diff',ascending=False)"
+  
+   ]
+  
+  },
+  
+  {
+  
+   "cell_type": "code",
+  
+   "execution_count": 68,
   "metadata": {},
   "outputs": [
    {
@@ -720,15 +731,85 @@
       "[89 rows x 5 columns]"
      ]
     },
-  
-     "execution_count": 49,
+  
+     "execution_count": 68,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
-  
-    "# let's see the pages with the largest diffs\n",
+  
+    "sorted"
+  
+   ]
+  
+  },
+  
+  {
+  
+   "cell_type": "markdown",
+  
+   "metadata": {},
+  
+   "source": [
+  
+    "# Screenshot the Fifteen Biggest Diffs?"
+  
+   ]
+  
+  },
+  
+  {
+  
+   "cell_type": "code",
+  
+   "execution_count": 80,
+  
+   "metadata": {},
+  
+   "outputs": [],
+  
+   "source": [
+  
+    "biggest_diffs = []\n",
+  
+    "for x in range(0,14):\n",
+  
+    "    biggest_diffs.append(\"https://wayback.archive-it.org/227/\" + sorted.iloc[x].tolist()[2][1:] + \"/\" + sorted.iloc[x].tolist()[3])"
+  
+   ]
+  
+  },
+  
+  {
+  
+   "cell_type": "code",
+  
+   "execution_count": 81,
+  
+   "metadata": {},
+  
+   "outputs": [
+  
+    {
+  
+     "data": {
+  
+      "text/plain": [
+  
+       "['https://wayback.archive-it.org/227/20141105/http://www.ndp.ca/',\n",
+  
+       " 'https://wayback.archive-it.org/227/20150206/http://www.ndp.ca/',\n",
+  
+       " 'https://wayback.archive-it.org/227/20140505/http://www.ndp.ca/',\n",
+  
+       " 'https://wayback.archive-it.org/227/20121103/http://www.ndp.ca/',\n",
+  
+       " 'https://wayback.archive-it.org/227/20080930/http://www.ndp.ca/',\n",
+  
+       " 'https://wayback.archive-it.org/227/20100803/http://www.ndp.ca/',\n",
+  
+       " 'https://wayback.archive-it.org/227/20150805/http://www.ndp.ca/',\n",
+  
+       " 'https://wayback.archive-it.org/227/20090802/http://www.ndp.ca/',\n",
+  
+       " 'https://wayback.archive-it.org/227/20091102/http://www.ndp.ca/',\n",
+  
+       " 'https://wayback.archive-it.org/227/20170205/http://www.ndp.ca/',\n",
+  
+       " 'https://wayback.archive-it.org/227/20130203/http://www.ndp.ca/',\n",
+  
+       " 'https://wayback.archive-it.org/227/20140205/http://www.ndp.ca/',\n",
+  
+       " 'https://wayback.archive-it.org/227/20101103/http://www.ndp.ca/',\n",
+  
+       " 'https://wayback.archive-it.org/227/20081103/http://www.ndp.ca/']"
+  
+      ]
+  
+     },
+  
+     "execution_count": 81,
+  
+     "metadata": {},
+  
+     "output_type": "execute_result"
+  
+    }
+  
+   ],
+  
+   "source": [
+  
+    "biggest_diffs"
+  
+   ]
+  
+  },
+  
+  {
+  
+   "cell_type": "code",
+  
+   "execution_count": 104,
+  
+   "metadata": {},
+  
+   "outputs": [],
+  
+   "source": [
+  
+    "from selenium import webdriver\n",
+  
+    "\n",
+  
+    "DRIVER = 'chromedriver'\n",
+  
+    "driver = webdriver.Chrome(DRIVER)\n",
    "\n",
-  
-    "ndp_diffs.sort_values('diff',ascending=False)"
+  
+    "count=1\n",
+  
+    "for page in biggest_diffs:\n",
+  
+    "    driver.get(page)\n",
+  
+    "    export_file=str(count)+\"-ndp.png\"\n",
+  
+    "    count=count+1\n",
+  
+    "    screenshot = driver.save_screenshot(export_file)\n",
+  
+    "    \n",
+  
+    "driver.quit()"
   ]
  },
  {

diff --git a/ndp-diff-images/1-ndp.png b/ndp-diff-images/1-ndp.png
diff --git a/ndp-diff-images/10-ndp.png b/ndp-diff-images/10-ndp.png
diff --git a/ndp-diff-images/11-ndp.png b/ndp-diff-images/11-ndp.png
diff --git a/ndp-diff-images/12-ndp.png b/ndp-diff-images/12-ndp.png
diff --git a/ndp-diff-images/13-ndp.png b/ndp-diff-images/13-ndp.png
diff --git a/ndp-diff-images/14-ndp.png b/ndp-diff-images/14-ndp.png
diff --git a/ndp-diff-images/2-ndp.png b/ndp-diff-images/2-ndp.png
diff --git a/ndp-diff-images/3-ndp.png b/ndp-diff-images/3-ndp.png
diff --git a/ndp-diff-images/4-ndp.png b/ndp-diff-images/4-ndp.png
diff --git a/ndp-diff-images/5-ndp.png b/ndp-diff-images/5-ndp.png
diff --git a/ndp-diff-images/6-ndp.png b/ndp-diff-images/6-ndp.png
diff --git a/ndp-diff-images/7-ndp.png b/ndp-diff-images/7-ndp.png
diff --git a/ndp-diff-images/8-ndp.png b/ndp-diff-images/8-ndp.png
diff --git a/ndp-diff-images/9-ndp.png b/ndp-diff-images/9-ndp.png
diff --git a/ndp-diff-images/my_screenshot.png b/ndp-diff-images/my_screenshot.png