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
290
291
292
293
294
295
| | #!/usr/bin/env python3
| | """
| | QuizVDS SPL Exam Questions Scraper
| | Scrapes all SPL questions from quizvds.it and saves them as markdown files.
| | """
| |
| | import requests
| | from bs4 import BeautifulSoup
| | import json
| | import time
| | import re
| | import os
| | from pathlib import Path
| |
| | BASE_URL = "https://quizvds.it"
| | HEADERS = {
| | "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
| | "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
| | "Accept-Language": "en-US,en;q=0.5",
| | "Connection": "keep-alive",
| | }
| |
| | OUTPUT_DIR = Path("/Users/i052341/Daten/Cloud/04 - Ablage/Ablage 2020 - 2029/Ablage 2025/Hobbies 2025/Segelflug/Theorie/Glidr/QuizVDS")
| |
| | SUBJECTS = [
| | ("10", "Air Law", "air-law"),
| | ("20", "Aircraft General Knowledge", "aircraft-general-knowledge"),
| | ("30", "Flight Performance and Planning", "flight-performance-and-planning"),
| | ("40", "Human Performance and Limitations", "human-performance-and-limitations"),
| | ("50", "Meteorology", "meteorology"),
| | ("60", "Navigation", "navigation"),
| | ("70", "Operational Procedures", "operational-procedures"),
| | ("80", "Principles of Flight", "principle-of-flight-aeroplane"),
| | ("90", "Communication", "communication"),
| | ]
| |
| | LANGUAGES = [
| | ("en-en", "English"),
| | # ("it-it", "Italian"), # Uncomment if Italian version needed
| | ]
| |
| |
| | def get_page(url, retries=3):
| | """Fetch a page with retry logic."""
| | for attempt in range(retries):
| | try:
| | resp = requests.get(url, headers=HEADERS, timeout=15)
| | resp.raise_for_status()
| | return resp.text
| | except Exception as e:
| | if attempt < retries - 1:
| | print(f" Retry {attempt + 1} for {url}: {e}")
| | time.sleep(2)
| | else:
| | print(f" FAILED after {retries} attempts: {url}: {e}")
| | return None
| | return None
| |
| |
| | def get_question_urls_from_listing(lang_code, subject_slug):
| | """Get all question URLs from the listing pages for a subject."""
| | question_urls = []
| |
| | for page_num in range(1, 50): # Max 50 pages per subject
| | if page_num == 1:
| | url = f"{BASE_URL}/{lang_code}/quiz/spl-en/{subject_slug}"
| | else:
| | url = f"{BASE_URL}/{lang_code}/quiz/spl-en/{subject_slug}/page{page_num}"
| |
| | html = get_page(url)
| | if not html:
| | break
| |
| | soup = BeautifulSoup(html, "html.parser")
| |
| | # Find all question links in the table
| | table = soup.find("table")
| | if not table:
| | break
| |
| | links = table.find_all("a", href=True)
| | # Question links have the subject slug and a numeric ID, exclude /page links
| | page_links = [
| | a["href"] for a in links
| | if f"/quiz/spl-en/{subject_slug}/" in a["href"]
| | and "/page" not in a["href"]
| | ]
| |
| | if not page_links:
| | break
| |
| | question_urls.extend(page_links)
| | print(f" Page {page_num}: found {len(page_links)} questions (total: {len(question_urls)})")
| |
| | time.sleep(0.3)
| |
| | return question_urls
| |
| |
| | def parse_question_page(html, url):
| | """Parse a question page and extract Q&A data."""
| | if not html:
| | return None
| |
| | soup = BeautifulSoup(html, "html.parser")
| |
| | # Extract from JSON-LD structured data (most reliable)
| | question_text = None
| | correct_answer = None
| | all_answers = []
| |
| | for script in soup.find_all("script", type="application/ld+json"):
| | try:
| | data = json.loads(script.string)
| | if data.get("@type") == "QAPage":
| | main = data.get("mainEntity", {})
| | question_text = main.get("name", "")
| | accepted = main.get("acceptedAnswer", {})
| | correct_answer = accepted.get("text", "")
| | suggested = main.get("suggestedAnswer", [])
| | all_wrong = [s.get("text", "") for s in suggested]
| | except (json.JSONDecodeError, AttributeError):
| | pass
| |
| | if not question_text:
| | return None
| |
| | # Get answers from the HTML table (preserves order A/B/C/D)
| | table = soup.find("table")
| | answers_from_table = []
| | if table:
| | for row in table.find_all("tr"):
| | cell = row.find("td")
| | if cell:
| | text = cell.get_text(strip=True)
| | is_correct = row.get("class") and "success" in row.get("class", [])
| | answers_from_table.append((text, is_correct))
| |
| | # Build final answer list
| | if answers_from_table:
| | final_answers = answers_from_table
| | else:
| | # Fallback: reconstruct from JSON-LD
| | wrong = all_wrong if 'all_wrong' in dir() else []
| | final_answers = [(correct_answer, True)] + [(a, False) for a in wrong]
| |
| | return {
| | "question": question_text,
| | "answers": final_answers,
| | "correct_answer": correct_answer,
| | "url": url,
| | }
| |
| |
| | def format_question_markdown(q_num, data):
| | """Format a question as markdown."""
| | letters = ["A", "B", "C", "D", "E"]
| | question = data["question"]
| | answers = data["answers"]
| | correct_answer = data["correct_answer"]
| |
| | lines = [
| | f"### Q{q_num}: {question} ^q{q_num}",
| | ]
| |
| | correct_letter = None
| | for i, (ans_text, is_correct) in enumerate(answers):
| | letter = letters[i]
| | lines.append(f"- {letter}) {ans_text}")
| | if is_correct or ans_text == correct_answer:
| | correct_letter = letter
| |
| | if correct_letter:
| | lines.append(f"**Correct: {correct_letter})**")
| | else:
| | lines.append(f"**Correct: ?)** <!-- {correct_answer} -->")
| |
| | lines.append("")
| | lines.append("> **Explanation:** ")
| | lines.append("")
| |
| | return "\n".join(lines)
| |
| |
| | def scrape_subject(lang_code, subject_code, subject_name, subject_slug):
| | """Scrape all questions for a subject."""
| | print(f"\n Scraping {subject_name} ({subject_slug})...")
| |
| | # Get all question URLs from listing pages
| | question_urls = get_question_urls_from_listing(lang_code, subject_slug)
| | print(f" Found {len(question_urls)} question URLs")
| |
| | if not question_urls:
| | print(f" WARNING: No questions found for {subject_name}")
| | return 0
| |
| | questions = []
| | for i, url in enumerate(question_urls, 1):
| | # Make URL absolute
| | if url.startswith("/"):
| | full_url = BASE_URL + url
| | else:
| | full_url = url
| |
| | html = get_page(full_url)
| | data = parse_question_page(html, full_url)
| |
| | if data:
| | questions.append(data)
| | if i % 10 == 0:
| | print(f" Scraped {i}/{len(question_urls)} questions...")
| | else:
| | print(f" WARNING: Failed to parse question {i}: {full_url}")
| |
| | time.sleep(0.2) # Be polite to the server
| |
| | return questions
| |
| |
| | def save_subject_markdown(subject_code, subject_name, questions, lang_suffix=""):
| | """Save questions to a markdown file."""
| | filename = f"{subject_code} - {subject_name}{lang_suffix}.md"
| | filepath = OUTPUT_DIR / filename
| |
| | lines = [
| | f"# {subject_code} - {subject_name}",
| | "",
| | f"Total questions: {len(questions)}",
| | "",
| | "---",
| | "",
| | ]
| |
| | for i, data in enumerate(questions, 1):
| | lines.append(format_question_markdown(i, data))
| | lines.append("---")
| | lines.append("")
| |
| | content = "\n".join(lines)
| |
| | with open(filepath, "w", encoding="utf-8") as f:
| | f.write(content)
| |
| | print(f" Saved {len(questions)} questions to: {filename}")
| | return filepath
| |
| |
| | def main():
| | """Main scraping function."""
| | print("QuizVDS SPL Exam Questions Scraper")
| | print("=" * 50)
| |
| | summary = {}
| |
| | for lang_code, lang_name in LANGUAGES:
| | print(f"\nLanguage: {lang_name} ({lang_code})")
| | print("-" * 40)
| |
| | lang_suffix = "" if lang_code == "en-en" else f" ({lang_name})"
| |
| | for subject_code, subject_name, subject_slug in SUBJECTS:
| | questions = scrape_subject(lang_code, subject_code, subject_name, subject_slug)
| |
| | if questions:
| | save_subject_markdown(subject_code, subject_name, questions, lang_suffix)
| | summary[f"{subject_code} - {subject_name}"] = len(questions)
| | else:
| | summary[f"{subject_code} - {subject_name}"] = 0
| |
| | # Write summary
| | print("\n" + "=" * 50)
| | print("SUMMARY")
| | print("=" * 50)
| | total = 0
| | for subject, count in summary.items():
| | print(f" {subject}: {count} questions")
| | total += count
| | print(f"\n TOTAL: {total} questions")
| |
| | # Save summary to file
| | summary_path = OUTPUT_DIR / "SUMMARY.md"
| | with open(summary_path, "w") as f:
| | f.write("# QuizVDS SPL Scraping Summary\n\n")
| | f.write(f"Scraped on: 2026-03-17\n\n")
| | f.write("| Subject | Questions |\n")
| | f.write("|---------|----------|\n")
| | for subject, count in summary.items():
| | f.write(f"| {subject} | {count} |\n")
| | f.write(f"\n**Total: {total} questions**\n")
| |
| | print(f"\nSummary saved to: {summary_path}")
| |
| |
| | if __name__ == "__main__":
| | main()
|
|
