make clear file.close() will make data appear in the written csv; add…

… print()s; cleanup earlier runs
ireapps · Mar 5, 2020 · 692de55 · 692de55
1 parent d260647
commit 692de55
Showing 1 changed file with 25 additions and 22 deletions.
diff --git a/completed/scraper_notebook_complete.ipynb b/completed/scraper_notebook_complete.ipynb
@@ -16,7 +16,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -34,7 +34,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -50,11 +50,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "html = r.text"
+    "html = r.text\n",
+    "print(html)"
    ]
   },
   {
@@ -78,11 +79,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "soup = BeautifulSoup(html, \"html.parser\")"
+    "soup = BeautifulSoup(html, \"html.parser\")\n",
+    "print(soup)"
    ]
   },
   {
@@ -94,11 +96,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "table = soup.find('table',{'class':'entChartTable'})"
+    "table = soup.find('table',{'class':'entChartTable'})\n",
+    "print(table)"
    ]
   },
   {
@@ -110,13 +113,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
     "rows = table.find_all('tr')\n",
-    "\n",
-    "rows = rows[2:]"
+    "# print(rows)\n",
+    "#skip the blank rows\n",
+    "rows = rows[2:]\n",
+    "# print(rows)"
    ]
   },
   {
@@ -128,7 +133,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -144,7 +149,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -171,26 +176,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "output = csv.DictWriter(csvfile, fieldnames = fieldnames, delimiter=',',quotechar='\"',quoting=csv.QUOTE_MINIMAL)\n",
-	"output.writeheader()"
-
+    "output = csv.DictWriter(csvfile, fieldnames=fieldnames, delimiter=',',quotechar='\"',quoting=csv.QUOTE_MINIMAL)\n",
+    "output.writeheader()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
     "#loop through the rows\n",
     "for row in rows:\n",
     "    #grab the table cells from each row\n",
     "    cells = row.find_all('td')\n",
-    "    #skip the blank rows\n",
     "    #create a dictionary and assign the cell values to keys in our dictionary\n",
     "    result = {\n",
     "        \"title\" : cells[0].text.strip(),\n",
@@ -214,12 +217,12 @@
     "collapsed": true
    },
    "source": [
-    "close the csv file"
+    "close the csv file to officially finish writing to it"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -246,7 +249,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.0"
+   "version": "3.6.8"
   }
  },
  "nbformat": 4,