Code cleanup

Author: REMitchell

v2/Chapter02-AdvancedHTMLParsing.ipynb

@@ -229,23 +229,21 @@
    "source": [
     "from urllib.request import urlopen\n",
     "from bs4 import BeautifulSoup\n",
-    "html = urlopen(\"http://www.pythonscraping.com/pages/warandpeace.html\")\n",
-    "bs = BeautifulSoup(html, \"html.parser\")\n",
-    "print(bs)"
+    "html = urlopen('http://www.pythonscraping.com/pages/warandpeace.html')\n",
+    "bsObj = BeautifulSoup(html, 'html.parser')\n",
+    "print(bsObj)"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 6,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "from urllib.request import urlopen\n",
     "from bs4 import BeautifulSoup\n",
-    "html = urlopen(\"http://www.pythonscraping.com/pages/warandpeace.html\")\n",
-    "bs = BeautifulSoup(html, \"html.parser\")"
+    "html = urlopen('http://www.pythonscraping.com/pages/warandpeace.html')\n",
+    "bsObj = BeautifulSoup(html, \"html.parser\")"
    ]
   },
   {
@@ -307,14 +305,14 @@
     }
    ],
    "source": [
-    "nameList = bs.findAll(\"span\", {\"class\":\"green\"})\n",
+    "nameList = bsObj.findAll('span', {'class':'green'})\n",
     "for name in nameList:\n",
     "    print(name.get_text())"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -326,13 +324,13 @@
     }
    ],
    "source": [
-    "titles = bs.find_all({\"h1\",\"h2\",\"h3\",\"h4\",\"h5\",\"h6\"})\n",
+    "titles = bsObj.find_all(['h1', 'h2','h3','h4','h5','h6'])\n",
     "print([title for title in titles])\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -416,7 +414,7 @@
     }
    ],
    "source": [
-    "allText = bs.find_all(\"span\", {\"class\":{\"green\", \"red\"}})\n",
+    "allText = bsObj.find_all('span', {'class':{'green', 'red'}})\n",
     "print([text for text in allText])"
    ]
   },
@@ -434,7 +432,7 @@
     }
    ],
    "source": [
-    "nameList = bs.find_all(text=\"the prince\")\n",
+    "nameList = bsObj.find_all(text='the prince')\n",
     "print(len(nameList))"
    ]
   },
@@ -452,7 +450,7 @@
     }
    ],
    "source": [
-    "allText = bs.find_all(id=\"title\", class_=\"text\")\n",
+    "allText = bsObj.find_all(id='title', class_='text')\n",
     "print([text for text in allText])"
    ]
   },
@@ -541,10 +539,10 @@
     "from urllib.request import urlopen\n",
     "from bs4 import BeautifulSoup\n",
     "\n",
-    "html = urlopen(\"http://www.pythonscraping.com/pages/page3.html\")\n",
-    "bs = BeautifulSoup(html, \"html.parser\")\n",
+    "html = urlopen('http://www.pythonscraping.com/pages/page3.html')\n",
+    "bsObj = BeautifulSoup(html, 'html.parser')\n",
     "\n",
-    "for child in bs.find(\"table\",{\"id\":\"giftList\"}).children:\n",
+    "for child in bsObj.find('table',{'id':'giftList'}).children:\n",
     "    print(child)"
    ]
   },
@@ -621,16 +619,16 @@
    "source": [
     "from urllib.request import urlopen\n",
     "from bs4 import BeautifulSoup\n",
-    "html = urlopen(\"http://www.pythonscraping.com/pages/page3.html\")\n",
-    "bs = BeautifulSoup(html, \"html.parser\")\n",
+    "html = urlopen('http://www.pythonscraping.com/pages/page3.html')\n",
+    "bsObj = BeautifulSoup(html, 'html.parser')\n",
     "\n",
-    "for sibling in bs.find(\"table\",{\"id\":\"giftList\"}).tr.next_siblings:\n",
+    "for sibling in bsObj.find('table', {'id':'giftList'}).tr.next_siblings:\n",
     "    print(sibling) "
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
@@ -647,14 +645,14 @@
     "from urllib.request import urlopen\n",
     "from bs4 import BeautifulSoup\n",
     "\n",
-    "html = urlopen(\"http://www.pythonscraping.com/pages/page3.html\")\n",
-    "bs = BeautifulSoup(html, \"html.parser\")\n",
-    "print(bs.find(\"img\",{\"src\":\"../img/gifts/img1.jpg\"}).parent.previous_sibling.get_text())"
+    "html = urlopen('http://www.pythonscraping.com/pages/page3.html')\n",
+    "bsObj = BeautifulSoup(html, 'html.parser')\n",
+    "print(bsObj.find('img',{'src':'../img/gifts/img1.jpg'}).parent.previous_sibling.get_text())"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -674,11 +672,11 @@
     "from bs4 import BeautifulSoup\n",
     "import re\n",
     "\n",
-    "html = urlopen(\"http://www.pythonscraping.com/pages/page3.html\")\n",
-    "bs = BeautifulSoup(html, \"html.parser\")\n",
-    "images = bs.find_all(\"img\", {\"src\":re.compile(\"\\.\\.\\/img\\/gifts/img.*\\.jpg\")})\n",
+    "html = urlopen('http://www.pythonscraping.com/pages/page3.html')\n",
+    "bsObj = BeautifulSoup(html, 'html.parser')\n",
+    "images = bsObj.find_all('img', {'src':re.compile('\\.\\.\\/img\\/gifts/img.*\\.jpg')})\n",
     "for image in images: \n",
-    "    print(image[\"src\"])"
+    "    print(image['src'])"
    ]
   },
   {
@@ -744,7 +742,7 @@
     }
    ],
    "source": [
-    "bs.find_all(lambda tag: len(tag.attrs) == 2)"
+    "bsObj.find_all(lambda tag: len(tag.attrs) == 2)"
    ]
   },
   {