File size: 10,007 Bytes
bacabb7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Web Scraping von Quotes\n",
    "\n",
    "In diesem Notebook lernen wir, wie man die Website [Quotes to Scrape](https://quotes.toscrape.com/) mit Python und `BeautifulSoup` scrapt. Diese Seite ist ein gutes Beispiel, um das Scraping von Zitaten und Autoren zu üben."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: requests in /home/codespace/.local/lib/python3.12/site-packages (2.32.3)\n",
      "Requirement already satisfied: beautifulsoup4 in /home/codespace/.local/lib/python3.12/site-packages (4.12.3)\n",
      "Requirement already satisfied: pandas in /home/codespace/.local/lib/python3.12/site-packages (2.2.3)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in /home/codespace/.local/lib/python3.12/site-packages (from requests) (3.3.2)\n",
      "Requirement already satisfied: idna<4,>=2.5 in /home/codespace/.local/lib/python3.12/site-packages (from requests) (3.10)\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in /home/codespace/.local/lib/python3.12/site-packages (from requests) (2.2.3)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in /home/codespace/.local/lib/python3.12/site-packages (from requests) (2024.8.30)\n",
      "Requirement already satisfied: soupsieve>1.2 in /home/codespace/.local/lib/python3.12/site-packages (from beautifulsoup4) (2.6)\n",
      "Requirement already satisfied: numpy>=1.26.0 in /usr/local/python/3.12.1/lib/python3.12/site-packages (from pandas) (1.26.4)\n",
      "Requirement already satisfied: python-dateutil>=2.8.2 in /home/codespace/.local/lib/python3.12/site-packages (from pandas) (2.9.0.post0)\n",
      "Requirement already satisfied: pytz>=2020.1 in /home/codespace/.local/lib/python3.12/site-packages (from pandas) (2024.2)\n",
      "Requirement already satisfied: tzdata>=2022.7 in /home/codespace/.local/lib/python3.12/site-packages (from pandas) (2024.2)\n",
      "Requirement already satisfied: six>=1.5 in /home/codespace/.local/lib/python3.12/site-packages (from python-dateutil>=2.8.2->pandas) (1.16.0)\n",
      "\n",
      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m24.2\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.3.1\u001b[0m\n",
      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpython3 -m pip install --upgrade pip\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "# Installieren der benötigten Bibliotheken\n",
    "! pip install requests beautifulsoup4 pandas"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Schritt 1: HTML-Inhalt abrufen\n",
    "\n",
    "Wir verwenden die `requests`-Bibliothek, um den HTML-Inhalt der Seite abzurufen."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "HTML-Inhalt erfolgreich abgerufen.\n"
     ]
    }
   ],
   "source": [
    "import requests\n",
    "\n",
    "# URL der Website\n",
    "url = \"https://quotes.toscrape.com/\"\n",
    "\n",
    "# HTML-Inhalt abrufen\n",
    "response = requests.get(url)\n",
    "\n",
    "# Überprüfen, ob die Anfrage erfolgreich war\n",
    "if response.status_code == 200:\n",
    "    print(\"HTML-Inhalt erfolgreich abgerufen.\")\n",
    "else:\n",
    "    print(f\"Fehler beim Abrufen der Seite: {response.status_code}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Schritt 2: HTML mit BeautifulSoup parsen\n",
    "\n",
    "Jetzt parsen wir den abgerufenen HTML-Inhalt mit `BeautifulSoup`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Quotes to Scrape\n"
     ]
    }
   ],
   "source": [
    "from bs4 import BeautifulSoup\n",
    "\n",
    "# HTML-Inhalt parsen\n",
    "soup = BeautifulSoup(response.text, 'html.parser')\n",
    "\n",
    "# Überprüfen des Titels der Seite\n",
    "print(soup.title.string)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Schritt 3: Daten extrahieren\n",
    "\n",
    "Wir extrahieren nun die Zitate und die zugehörigen Autoren."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\"“The world as we have created it is a process of our thinking. It cannot be changed without changing our thinking.”\" - Albert Einstein\n",
      "\"“It is our choices, Harry, that show what we truly are, far more than our abilities.”\" - J.K. Rowling\n",
      "\"“There are only two ways to live your life. One is as though nothing is a miracle. The other is as though everything is a miracle.”\" - Albert Einstein\n",
      "\"“The person, be it gentleman or lady, who has not pleasure in a good novel, must be intolerably stupid.”\" - Jane Austen\n",
      "\"“Imperfection is beauty, madness is genius and it's better to be absolutely ridiculous than absolutely boring.”\" - Marilyn Monroe\n"
     ]
    }
   ],
   "source": [
    "# Listen zur Speicherung der Daten\n",
    "quotes = []\n",
    "authors = []\n",
    "\n",
    "# Alle Zitatcontainer finden\n",
    "quote_blocks = soup.find_all('div', class_='quote')\n",
    "\n",
    "# Daten extrahieren\n",
    "for block in quote_blocks:\n",
    "    quote = block.find('span', class_='text').text  # Zitat\n",
    "    author = block.find('small', class_='author').text  # Autor\n",
    "    quotes.append(quote)\n",
    "    authors.append(author)\n",
    "\n",
    "# Die ersten Zitate anzeigen\n",
    "for quote, author in zip(quotes[:5], authors[:5]):  # Nur die ersten 5 Zitate\n",
    "    print(f'\"{quote}\" - {author}')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Schritt 4: Daten in einem DataFrame speichern\n",
    "\n",
    "Um die extrahierten Daten zu speichern, verwenden wir `pandas`, um sie in einem DataFrame zu organisieren."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Quote</th>\n",
       "      <th>Author</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>“The world as we have created it is a process ...</td>\n",
       "      <td>Albert Einstein</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>“It is our choices, Harry, that show what we t...</td>\n",
       "      <td>J.K. Rowling</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>“There are only two ways to live your life. On...</td>\n",
       "      <td>Albert Einstein</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>“The person, be it gentleman or lady, who has ...</td>\n",
       "      <td>Jane Austen</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>“Imperfection is beauty, madness is genius and...</td>\n",
       "      <td>Marilyn Monroe</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                               Quote           Author\n",
       "0  “The world as we have created it is a process ...  Albert Einstein\n",
       "1  “It is our choices, Harry, that show what we t...     J.K. Rowling\n",
       "2  “There are only two ways to live your life. On...  Albert Einstein\n",
       "3  “The person, be it gentleman or lady, who has ...      Jane Austen\n",
       "4  “Imperfection is beauty, madness is genius and...   Marilyn Monroe"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "# DataFrame erstellen\n",
    "quotes_df = pd.DataFrame({\n",
    "    'Quote': quotes,\n",
    "    'Author': authors\n",
    "})\n",
    "\n",
    "# DataFrame anzeigen\n",
    "quotes_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Fazit\n",
    "\n",
    "In diesem Notebook haben wir gelernt, wie man die Website [Quotes to Scrape](https://quotes.toscrape.com/) mit Python und `BeautifulSoup` scrapt. Wir haben die Zitate und ihre Autoren extrahiert und in einem DataFrame gespeichert."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}