webscout 8.3.6__py3-none-any.whl → 2025.10.11__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.

This version of webscout might be problematic. Click here for more details.

Files changed (304) hide show
  1. webscout/AIauto.py +250 -250
  2. webscout/AIbase.py +379 -379
  3. webscout/AIutel.py +60 -58
  4. webscout/Bard.py +1012 -1012
  5. webscout/Bing_search.py +417 -417
  6. webscout/DWEBS.py +529 -529
  7. webscout/Extra/Act.md +309 -309
  8. webscout/Extra/GitToolkit/__init__.py +10 -10
  9. webscout/Extra/GitToolkit/gitapi/README.md +110 -110
  10. webscout/Extra/GitToolkit/gitapi/__init__.py +11 -11
  11. webscout/Extra/GitToolkit/gitapi/repository.py +195 -195
  12. webscout/Extra/GitToolkit/gitapi/user.py +96 -96
  13. webscout/Extra/GitToolkit/gitapi/utils.py +61 -61
  14. webscout/Extra/YTToolkit/README.md +375 -375
  15. webscout/Extra/YTToolkit/YTdownloader.py +956 -956
  16. webscout/Extra/YTToolkit/__init__.py +2 -2
  17. webscout/Extra/YTToolkit/transcriber.py +475 -475
  18. webscout/Extra/YTToolkit/ytapi/README.md +44 -44
  19. webscout/Extra/YTToolkit/ytapi/__init__.py +6 -6
  20. webscout/Extra/YTToolkit/ytapi/channel.py +307 -307
  21. webscout/Extra/YTToolkit/ytapi/errors.py +13 -13
  22. webscout/Extra/YTToolkit/ytapi/extras.py +118 -118
  23. webscout/Extra/YTToolkit/ytapi/https.py +88 -88
  24. webscout/Extra/YTToolkit/ytapi/patterns.py +61 -61
  25. webscout/Extra/YTToolkit/ytapi/playlist.py +58 -58
  26. webscout/Extra/YTToolkit/ytapi/pool.py +7 -7
  27. webscout/Extra/YTToolkit/ytapi/query.py +39 -39
  28. webscout/Extra/YTToolkit/ytapi/stream.py +62 -62
  29. webscout/Extra/YTToolkit/ytapi/utils.py +62 -62
  30. webscout/Extra/YTToolkit/ytapi/video.py +232 -232
  31. webscout/Extra/autocoder/__init__.py +9 -9
  32. webscout/Extra/autocoder/autocoder.py +1105 -1105
  33. webscout/Extra/autocoder/autocoder_utiles.py +332 -332
  34. webscout/Extra/gguf.md +429 -429
  35. webscout/Extra/gguf.py +1213 -1213
  36. webscout/Extra/tempmail/README.md +487 -487
  37. webscout/Extra/tempmail/__init__.py +27 -27
  38. webscout/Extra/tempmail/async_utils.py +140 -140
  39. webscout/Extra/tempmail/base.py +160 -160
  40. webscout/Extra/tempmail/cli.py +186 -186
  41. webscout/Extra/tempmail/emailnator.py +84 -84
  42. webscout/Extra/tempmail/mail_tm.py +360 -360
  43. webscout/Extra/tempmail/temp_mail_io.py +291 -291
  44. webscout/Extra/weather.md +281 -281
  45. webscout/Extra/weather.py +193 -193
  46. webscout/Litlogger/README.md +10 -10
  47. webscout/Litlogger/__init__.py +15 -15
  48. webscout/Litlogger/formats.py +13 -13
  49. webscout/Litlogger/handlers.py +121 -121
  50. webscout/Litlogger/levels.py +13 -13
  51. webscout/Litlogger/logger.py +134 -134
  52. webscout/Provider/AISEARCH/Perplexity.py +332 -332
  53. webscout/Provider/AISEARCH/README.md +279 -279
  54. webscout/Provider/AISEARCH/__init__.py +33 -11
  55. webscout/Provider/AISEARCH/felo_search.py +206 -206
  56. webscout/Provider/AISEARCH/genspark_search.py +323 -323
  57. webscout/Provider/AISEARCH/hika_search.py +185 -185
  58. webscout/Provider/AISEARCH/iask_search.py +410 -410
  59. webscout/Provider/AISEARCH/monica_search.py +219 -219
  60. webscout/Provider/AISEARCH/scira_search.py +316 -314
  61. webscout/Provider/AISEARCH/stellar_search.py +177 -177
  62. webscout/Provider/AISEARCH/webpilotai_search.py +255 -255
  63. webscout/Provider/Aitopia.py +314 -315
  64. webscout/Provider/Andi.py +3 -3
  65. webscout/Provider/Apriel.py +306 -0
  66. webscout/Provider/ChatGPTClone.py +236 -236
  67. webscout/Provider/ChatSandbox.py +343 -342
  68. webscout/Provider/Cloudflare.py +324 -324
  69. webscout/Provider/Cohere.py +208 -207
  70. webscout/Provider/Deepinfra.py +370 -369
  71. webscout/Provider/ExaAI.py +260 -260
  72. webscout/Provider/ExaChat.py +308 -387
  73. webscout/Provider/Flowith.py +221 -221
  74. webscout/Provider/GMI.py +293 -0
  75. webscout/Provider/Gemini.py +164 -162
  76. webscout/Provider/GeminiProxy.py +167 -166
  77. webscout/Provider/GithubChat.py +371 -370
  78. webscout/Provider/Groq.py +800 -800
  79. webscout/Provider/HeckAI.py +383 -379
  80. webscout/Provider/Jadve.py +282 -297
  81. webscout/Provider/K2Think.py +308 -0
  82. webscout/Provider/Koboldai.py +206 -384
  83. webscout/Provider/LambdaChat.py +423 -425
  84. webscout/Provider/Nemotron.py +244 -245
  85. webscout/Provider/Netwrck.py +248 -247
  86. webscout/Provider/OLLAMA.py +395 -394
  87. webscout/Provider/OPENAI/Cloudflare.py +394 -395
  88. webscout/Provider/OPENAI/FalconH1.py +452 -457
  89. webscout/Provider/OPENAI/FreeGemini.py +297 -299
  90. webscout/Provider/OPENAI/{monochat.py → K2Think.py} +432 -329
  91. webscout/Provider/OPENAI/NEMOTRON.py +241 -244
  92. webscout/Provider/OPENAI/PI.py +428 -427
  93. webscout/Provider/OPENAI/README.md +959 -959
  94. webscout/Provider/OPENAI/TogetherAI.py +345 -345
  95. webscout/Provider/OPENAI/TwoAI.py +466 -467
  96. webscout/Provider/OPENAI/__init__.py +33 -59
  97. webscout/Provider/OPENAI/ai4chat.py +313 -303
  98. webscout/Provider/OPENAI/base.py +249 -269
  99. webscout/Provider/OPENAI/chatglm.py +528 -0
  100. webscout/Provider/OPENAI/chatgpt.py +593 -588
  101. webscout/Provider/OPENAI/chatgptclone.py +521 -524
  102. webscout/Provider/OPENAI/chatsandbox.py +202 -177
  103. webscout/Provider/OPENAI/deepinfra.py +319 -315
  104. webscout/Provider/OPENAI/e2b.py +1665 -1665
  105. webscout/Provider/OPENAI/exaai.py +420 -420
  106. webscout/Provider/OPENAI/exachat.py +452 -452
  107. webscout/Provider/OPENAI/friendli.py +232 -232
  108. webscout/Provider/OPENAI/{refact.py → gmi.py} +324 -274
  109. webscout/Provider/OPENAI/groq.py +364 -364
  110. webscout/Provider/OPENAI/heckai.py +314 -311
  111. webscout/Provider/OPENAI/llmchatco.py +337 -337
  112. webscout/Provider/OPENAI/netwrck.py +355 -354
  113. webscout/Provider/OPENAI/oivscode.py +290 -290
  114. webscout/Provider/OPENAI/opkfc.py +518 -518
  115. webscout/Provider/OPENAI/pydantic_imports.py +1 -1
  116. webscout/Provider/OPENAI/scirachat.py +535 -529
  117. webscout/Provider/OPENAI/sonus.py +308 -308
  118. webscout/Provider/OPENAI/standardinput.py +442 -442
  119. webscout/Provider/OPENAI/textpollinations.py +340 -348
  120. webscout/Provider/OPENAI/toolbaz.py +419 -413
  121. webscout/Provider/OPENAI/typefully.py +362 -362
  122. webscout/Provider/OPENAI/utils.py +295 -295
  123. webscout/Provider/OPENAI/venice.py +436 -436
  124. webscout/Provider/OPENAI/wisecat.py +387 -387
  125. webscout/Provider/OPENAI/writecream.py +166 -166
  126. webscout/Provider/OPENAI/x0gpt.py +378 -378
  127. webscout/Provider/OPENAI/yep.py +389 -389
  128. webscout/Provider/OpenGPT.py +230 -230
  129. webscout/Provider/Openai.py +244 -496
  130. webscout/Provider/PI.py +405 -404
  131. webscout/Provider/Perplexitylabs.py +430 -431
  132. webscout/Provider/QwenLM.py +272 -254
  133. webscout/Provider/STT/__init__.py +32 -2
  134. webscout/Provider/{Llama3.py → Sambanova.py} +257 -258
  135. webscout/Provider/StandardInput.py +309 -309
  136. webscout/Provider/TTI/README.md +82 -82
  137. webscout/Provider/TTI/__init__.py +33 -12
  138. webscout/Provider/TTI/aiarta.py +413 -413
  139. webscout/Provider/TTI/base.py +136 -136
  140. webscout/Provider/TTI/bing.py +243 -243
  141. webscout/Provider/TTI/gpt1image.py +149 -149
  142. webscout/Provider/TTI/imagen.py +196 -196
  143. webscout/Provider/TTI/infip.py +211 -211
  144. webscout/Provider/TTI/magicstudio.py +232 -232
  145. webscout/Provider/TTI/monochat.py +219 -219
  146. webscout/Provider/TTI/piclumen.py +214 -214
  147. webscout/Provider/TTI/pixelmuse.py +232 -232
  148. webscout/Provider/TTI/pollinations.py +232 -232
  149. webscout/Provider/TTI/together.py +288 -288
  150. webscout/Provider/TTI/utils.py +12 -12
  151. webscout/Provider/TTI/venice.py +367 -367
  152. webscout/Provider/TTS/README.md +192 -192
  153. webscout/Provider/TTS/__init__.py +33 -10
  154. webscout/Provider/TTS/parler.py +110 -110
  155. webscout/Provider/TTS/streamElements.py +333 -333
  156. webscout/Provider/TTS/utils.py +280 -280
  157. webscout/Provider/TeachAnything.py +237 -236
  158. webscout/Provider/TextPollinationsAI.py +311 -318
  159. webscout/Provider/TogetherAI.py +356 -357
  160. webscout/Provider/TwoAI.py +313 -569
  161. webscout/Provider/TypliAI.py +312 -311
  162. webscout/Provider/UNFINISHED/ChatHub.py +208 -208
  163. webscout/Provider/UNFINISHED/ChutesAI.py +313 -313
  164. webscout/Provider/{GizAI.py → UNFINISHED/GizAI.py} +294 -294
  165. webscout/Provider/{Marcus.py → UNFINISHED/Marcus.py} +198 -198
  166. webscout/Provider/{Qodo.py → UNFINISHED/Qodo.py} +477 -477
  167. webscout/Provider/UNFINISHED/VercelAIGateway.py +338 -338
  168. webscout/Provider/{XenAI.py → UNFINISHED/XenAI.py} +324 -324
  169. webscout/Provider/UNFINISHED/Youchat.py +330 -330
  170. webscout/Provider/UNFINISHED/liner.py +334 -0
  171. webscout/Provider/UNFINISHED/liner_api_request.py +262 -262
  172. webscout/Provider/UNFINISHED/puterjs.py +634 -634
  173. webscout/Provider/UNFINISHED/samurai.py +223 -223
  174. webscout/Provider/UNFINISHED/test_lmarena.py +119 -119
  175. webscout/Provider/Venice.py +251 -250
  176. webscout/Provider/VercelAI.py +256 -255
  177. webscout/Provider/WiseCat.py +232 -231
  178. webscout/Provider/WrDoChat.py +367 -366
  179. webscout/Provider/__init__.py +33 -86
  180. webscout/Provider/ai4chat.py +174 -174
  181. webscout/Provider/akashgpt.py +331 -334
  182. webscout/Provider/cerebras.py +446 -340
  183. webscout/Provider/chatglm.py +394 -214
  184. webscout/Provider/cleeai.py +211 -212
  185. webscout/Provider/deepseek_assistant.py +1 -1
  186. webscout/Provider/elmo.py +282 -282
  187. webscout/Provider/geminiapi.py +208 -208
  188. webscout/Provider/granite.py +261 -261
  189. webscout/Provider/hermes.py +263 -265
  190. webscout/Provider/julius.py +223 -222
  191. webscout/Provider/learnfastai.py +309 -309
  192. webscout/Provider/llama3mitril.py +214 -214
  193. webscout/Provider/llmchat.py +243 -243
  194. webscout/Provider/llmchatco.py +290 -290
  195. webscout/Provider/meta.py +801 -801
  196. webscout/Provider/oivscode.py +309 -309
  197. webscout/Provider/scira_chat.py +384 -457
  198. webscout/Provider/searchchat.py +292 -291
  199. webscout/Provider/sonus.py +258 -258
  200. webscout/Provider/toolbaz.py +370 -364
  201. webscout/Provider/turboseek.py +274 -265
  202. webscout/Provider/typefully.py +208 -207
  203. webscout/Provider/x0gpt.py +1 -0
  204. webscout/Provider/yep.py +372 -371
  205. webscout/__init__.py +30 -31
  206. webscout/__main__.py +5 -5
  207. webscout/auth/api_key_manager.py +189 -189
  208. webscout/auth/config.py +175 -175
  209. webscout/auth/models.py +185 -185
  210. webscout/auth/routes.py +664 -664
  211. webscout/auth/simple_logger.py +236 -236
  212. webscout/cli.py +523 -523
  213. webscout/conversation.py +438 -438
  214. webscout/exceptions.py +361 -361
  215. webscout/litagent/Readme.md +298 -298
  216. webscout/litagent/__init__.py +28 -28
  217. webscout/litagent/agent.py +581 -581
  218. webscout/litagent/constants.py +59 -59
  219. webscout/litprinter/__init__.py +58 -58
  220. webscout/models.py +181 -181
  221. webscout/optimizers.py +419 -419
  222. webscout/prompt_manager.py +288 -288
  223. webscout/sanitize.py +1078 -1078
  224. webscout/scout/README.md +401 -401
  225. webscout/scout/__init__.py +8 -8
  226. webscout/scout/core/__init__.py +6 -6
  227. webscout/scout/core/crawler.py +297 -297
  228. webscout/scout/core/scout.py +706 -706
  229. webscout/scout/core/search_result.py +95 -95
  230. webscout/scout/core/text_analyzer.py +62 -62
  231. webscout/scout/core/text_utils.py +277 -277
  232. webscout/scout/core/web_analyzer.py +51 -51
  233. webscout/scout/element.py +599 -599
  234. webscout/scout/parsers/__init__.py +69 -69
  235. webscout/scout/parsers/html5lib_parser.py +172 -172
  236. webscout/scout/parsers/html_parser.py +236 -236
  237. webscout/scout/parsers/lxml_parser.py +178 -178
  238. webscout/scout/utils.py +37 -37
  239. webscout/swiftcli/Readme.md +323 -323
  240. webscout/swiftcli/__init__.py +95 -95
  241. webscout/swiftcli/core/__init__.py +7 -7
  242. webscout/swiftcli/core/cli.py +308 -308
  243. webscout/swiftcli/core/context.py +104 -104
  244. webscout/swiftcli/core/group.py +241 -241
  245. webscout/swiftcli/decorators/__init__.py +28 -28
  246. webscout/swiftcli/decorators/command.py +221 -221
  247. webscout/swiftcli/decorators/options.py +220 -220
  248. webscout/swiftcli/decorators/output.py +302 -302
  249. webscout/swiftcli/exceptions.py +21 -21
  250. webscout/swiftcli/plugins/__init__.py +9 -9
  251. webscout/swiftcli/plugins/base.py +135 -135
  252. webscout/swiftcli/plugins/manager.py +269 -269
  253. webscout/swiftcli/utils/__init__.py +59 -59
  254. webscout/swiftcli/utils/formatting.py +252 -252
  255. webscout/swiftcli/utils/parsing.py +267 -267
  256. webscout/update_checker.py +117 -117
  257. webscout/version.py +1 -1
  258. webscout/webscout_search.py +1183 -1183
  259. webscout/webscout_search_async.py +649 -649
  260. webscout/yep_search.py +346 -346
  261. webscout/zeroart/README.md +89 -89
  262. webscout/zeroart/__init__.py +134 -134
  263. webscout/zeroart/base.py +66 -66
  264. webscout/zeroart/effects.py +100 -100
  265. webscout/zeroart/fonts.py +1238 -1238
  266. {webscout-8.3.6.dist-info → webscout-2025.10.11.dist-info}/METADATA +937 -936
  267. webscout-2025.10.11.dist-info/RECORD +300 -0
  268. webscout/Provider/AISEARCH/DeepFind.py +0 -254
  269. webscout/Provider/AllenAI.py +0 -440
  270. webscout/Provider/Blackboxai.py +0 -793
  271. webscout/Provider/FreeGemini.py +0 -250
  272. webscout/Provider/GptOss.py +0 -207
  273. webscout/Provider/Hunyuan.py +0 -283
  274. webscout/Provider/Kimi.py +0 -445
  275. webscout/Provider/MCPCore.py +0 -322
  276. webscout/Provider/MiniMax.py +0 -207
  277. webscout/Provider/OPENAI/BLACKBOXAI.py +0 -1045
  278. webscout/Provider/OPENAI/MiniMax.py +0 -298
  279. webscout/Provider/OPENAI/Qwen3.py +0 -304
  280. webscout/Provider/OPENAI/autoproxy.py +0 -1067
  281. webscout/Provider/OPENAI/copilot.py +0 -321
  282. webscout/Provider/OPENAI/gptoss.py +0 -288
  283. webscout/Provider/OPENAI/kimi.py +0 -469
  284. webscout/Provider/OPENAI/mcpcore.py +0 -431
  285. webscout/Provider/OPENAI/multichat.py +0 -378
  286. webscout/Provider/OPENAI/qodo.py +0 -630
  287. webscout/Provider/OPENAI/xenai.py +0 -514
  288. webscout/Provider/Reka.py +0 -214
  289. webscout/Provider/UNFINISHED/fetch_together_models.py +0 -90
  290. webscout/Provider/asksteve.py +0 -220
  291. webscout/Provider/copilot.py +0 -441
  292. webscout/Provider/freeaichat.py +0 -294
  293. webscout/Provider/koala.py +0 -182
  294. webscout/Provider/lmarena.py +0 -198
  295. webscout/Provider/monochat.py +0 -275
  296. webscout/Provider/multichat.py +0 -375
  297. webscout/Provider/scnet.py +0 -244
  298. webscout/Provider/talkai.py +0 -194
  299. webscout/tempid.py +0 -128
  300. webscout-8.3.6.dist-info/RECORD +0 -327
  301. {webscout-8.3.6.dist-info → webscout-2025.10.11.dist-info}/WHEEL +0 -0
  302. {webscout-8.3.6.dist-info → webscout-2025.10.11.dist-info}/entry_points.txt +0 -0
  303. {webscout-8.3.6.dist-info → webscout-2025.10.11.dist-info}/licenses/LICENSE.md +0 -0
  304. {webscout-8.3.6.dist-info → webscout-2025.10.11.dist-info}/top_level.txt +0 -0
webscout/scout/README.md CHANGED
@@ -1,401 +1,401 @@
1
- **🚀 The Most Advanced HTML Parser & Web Crawler for AI/LLM Data Collection**
2
-
3
- **🌟 Built for the Future • Powered by Intelligence • Trusted by Developers**
4
-
5
-
6
- ## 📋 Overview
7
-
8
- Scout is an ultra-powerful, enterprise-grade HTML parsing and web crawling library designed for the AI era. Built with LLM data collection in mind, Scout provides unparalleled capabilities for extracting, analyzing, and processing web content at scale. With its BeautifulSoup-compatible API enhanced with modern features, Scout is the go-to solution for serious web scraping projects.
9
-
10
- <details open>
11
- <summary><b>🌟 Why Scout is the Ultimate Choice</b></summary>
12
-
13
- - **🧠 LLM-Optimized Crawling**: Purpose-built for collecting high-quality training data for Large Language Models
14
- - **🌐 Subdomain Intelligence**: Automatically discovers and crawls subdomains (e.g., blog.example.com, docs.example.com)
15
- - **⚡ Lightning-Fast Performance**: Multi-threaded concurrent crawling with intelligent rate limiting
16
- - **🎯 Surgical Precision**: Advanced content extraction that preserves structure while removing noise
17
- - **🔍 Deep Analysis**: Built-in NLP capabilities for entity extraction, text analysis, and semantic understanding
18
- - **🛡️ Enterprise-Ready**: Robust error handling, retry mechanisms, and respect for robots.txt
19
- - **📊 Rich Data Extraction**: Captures metadata, structured data, semantic content, and more
20
- - **🔄 Format Flexibility**: Export to JSON, Markdown, CSV, or custom formats
21
- - **🎨 BeautifulSoup++ API**: Familiar interface with 10x more features
22
-
23
- </details>
24
-
25
- ## 📑 Table of Contents
26
-
27
- - [Installation](#-installation)
28
- - [Quick Start](#-quick-start)
29
- - [Features](#-features)
30
- - [Advanced Usage](#-advanced-usage)
31
- - [API Reference](#-api-reference)
32
- - [Dependencies](#-dependencies)
33
- - [Supported Python Versions](#-supported-python-versions)
34
- - [Contributing](#-contributing)
35
- - [License](#-license)
36
-
37
- ## 📦 Installation
38
-
39
- ```bash
40
- pip install webscout
41
- ```
42
-
43
- Or install the latest version from GitHub:
44
-
45
- ```bash
46
- pip install git+https://github.com/OEvortex/Webscout.git
47
- ```
48
-
49
- ## 🚀 Quick Start
50
-
51
- ### Basic Parsing
52
-
53
- ```python
54
- from webscout.scout import Scout
55
-
56
- # Parse HTML content
57
- html_content = """
58
- <html>
59
- <body>
60
- <h1>Hello, Scout!</h1>
61
- <div class="content">
62
- <p>Web parsing made easy.</p>
63
- <a href="https://example.com">Link</a>
64
- </div>
65
- </body>
66
- </html>
67
- """
68
-
69
- scout = Scout(html_content)
70
-
71
- # Find elements
72
- title = scout.find('h1')
73
- links = scout.find_all('a')
74
-
75
- # Extract text
76
- print(title[0].get_text()) # Output: Hello, Scout!
77
- print(links.attrs('href')) # Output: ['https://example.com']
78
- ```
79
-
80
- ### Web Crawling
81
-
82
- ```python
83
- from webscout.scout import ScoutCrawler
84
-
85
- # Crawl a website with default settings
86
- crawler = ScoutCrawler('https://example.com') # Default: max_pages=50
87
-
88
- # Or customize the crawler
89
- crawler = ScoutCrawler(
90
- 'https://example.com', # base_url
91
- max_pages=100, # maximum pages to crawl
92
- tags_to_remove=['script', 'style', 'nav'] # tags to remove from content
93
- )
94
-
95
- # Start crawling
96
- crawled_pages = crawler.crawl()
97
-
98
- for page in crawled_pages:
99
- print(f"URL: {page['url']}")
100
- print(f"Title: {page['title']}")
101
- print(f"Links found: {len(page['links'])}")
102
- print(f"Crawl depth: {page['depth']}")
103
- ```
104
-
105
- ### Text Analysis
106
-
107
- ```python
108
- from webscout.scout import Scout
109
-
110
- # Parse a webpage
111
- html = """<div><h1>Climate Change</h1><p>Email us at info@example.com or call 555-123-4567.</p>
112
- <p>Visit https://climate-action.org for more information.</p></div>"""
113
- scout = Scout(html)
114
-
115
- # Analyze text and extract entities
116
- analysis = scout.analyze_text()
117
- print(f"Word frequencies: {analysis['word_count']}")
118
- print(f"Entities found: {analysis['entities']}")
119
- ```
120
-
121
- ## ✨ Features
122
-
123
- ### 🔍 Multiple Parser Support
124
-
125
- Scout supports multiple HTML/XML parsers, allowing you to choose the best tool for your specific needs:
126
-
127
- | Parser | Description | Best For |
128
- |--------|-------------|----------|
129
- | `html.parser` | Python's built-in parser | General-purpose parsing, no dependencies |
130
- | `lxml` | Fast C-based parser | Performance-critical applications |
131
- | `html5lib` | Highly compliant HTML5 parser | Handling malformed HTML |
132
- | `lxml-xml` | XML parser | XML document parsing |
133
-
134
- ```python
135
- # Choose your parser
136
- scout = Scout(html_content, features='lxml') # For speed
137
- scout = Scout(html_content, features='html5lib') # For compliance
138
- ```
139
-
140
- ### 🌐 Advanced Parsing Capabilities
141
-
142
- Scout provides powerful tools for navigating and manipulating HTML/XML documents:
143
-
144
- - **Element Selection**: Find elements by tag name, attributes, CSS selectors, and more
145
- - **Tree Traversal**: Navigate parent-child relationships and sibling elements
146
- - **Content Extraction**: Extract text, attributes, and structured data
147
- - **Document Manipulation**: Modify, replace, or remove elements
148
- - **Dynamic Building**: Easily append or insert new nodes
149
-
150
- ```python
151
- # CSS selector support
152
- elements = scout.select('div.content > p')
153
-
154
- # Advanced find with attribute matching
155
- results = scout.find_all('a', attrs={'class': 'external', 'rel': 'nofollow'})
156
-
157
- # Tree traversal
158
- parent = element.find_parent('div')
159
- siblings = element.find_next_siblings('p')
160
- prev_sibling = element.find_previous_sibling('p')
161
- ```
162
-
163
- ### 🧠 Intelligent Analysis
164
-
165
- Scout includes built-in analysis tools for extracting insights from web content:
166
-
167
- #### Text Analysis
168
-
169
- ```python
170
- # Extract and analyze text
171
- text = scout.get_text()
172
- word_counts = scout.text_analyzer.count_words(text)
173
- entities = scout.text_analyzer.extract_entities(text)
174
- ```
175
-
176
- #### Web Structure Analysis
177
-
178
- ```python
179
- # Analyze page structure
180
- structure = scout.analyze_page_structure()
181
- print(f"Most common tags: {structure['tag_distribution']}")
182
- print(f"Page depth: {max(structure['depth_analysis'].keys())}")
183
- ```
184
-
185
- #### Semantic Information Extraction
186
-
187
- ```python
188
- # Extract semantic information
189
- semantics = scout.extract_semantic_info()
190
- print(f"Headings: {semantics['headings']}")
191
- print(f"Lists: {len(semantics['lists']['ul']) + len(semantics['lists']['ol'])}")
192
- print(f"Tables: {semantics['tables']['count']}")
193
- ```
194
-
195
- ### 🕸️ Web Crawling
196
-
197
- Scout includes a powerful concurrent web crawler for fetching and analyzing multiple pages:
198
-
199
- ```python
200
- from webscout.scout import ScoutCrawler
201
-
202
- # Create a crawler with default settings
203
- crawler = ScoutCrawler('https://example.com') # Default: max_pages=50
204
-
205
- # Or customize the crawler with specific options
206
- crawler = ScoutCrawler(
207
- 'https://example.com', # base_url
208
- max_pages=100, # maximum pages to crawl
209
- tags_to_remove=['script', 'style', 'nav'] # tags to remove from content
210
- )
211
-
212
- # Start crawling
213
- pages = crawler.crawl()
214
-
215
- # Process results
216
- for page in pages:
217
- print(f"URL: {page['url']}")
218
- print(f"Title: {page['title']}")
219
- print(f"Links: {len(page['links'])}")
220
- print(f"Depth: {page['depth']}")
221
- ```
222
-
223
- The crawler automatically:
224
- - Stays within the same domain as the base URL
225
- - Uses concurrent requests for faster crawling
226
- - Removes unwanted tags (like scripts and styles) for cleaner text extraction
227
- - Tracks crawl depth for each page
228
-
229
- ### 📄 Format Conversion
230
-
231
- Scout can convert HTML to various formats:
232
-
233
- ```python
234
- # Convert to JSON
235
- json_data = scout.to_json(indent=2)
236
-
237
- # Convert to Markdown
238
- markdown = scout.to_markdown(heading_style='ATX')
239
-
240
- # Pretty-print HTML
241
- pretty_html = scout.prettify()
242
- ```
243
-
244
- ## 🔬 Advanced Usage
245
-
246
- ### Working with Search Results
247
-
248
- Scout's search methods return a `ScoutSearchResult` object with powerful methods for processing results:
249
-
250
- ```python
251
- from webscout.scout import Scout
252
-
253
- scout = Scout(html_content)
254
-
255
- # Find all paragraphs
256
- paragraphs = scout.find_all('p')
257
-
258
- # Extract all text from results
259
- all_text = paragraphs.texts(separator='\n')
260
-
261
- # Extract specific attributes
262
- hrefs = paragraphs.attrs('href')
263
-
264
- # Filter results with a predicate function
265
- important = paragraphs.filter(lambda p: 'important' in p.get('class', []))
266
-
267
- # Transform results
268
- word_counts = paragraphs.map(lambda p: len(p.get_text().split()))
269
-
270
- # Analyze text in results
271
- analysis = paragraphs.analyze_text()
272
- ```
273
-
274
- ### URL Handling and Analysis
275
-
276
- ```python
277
- from webscout.scout import Scout
278
-
279
- scout = Scout(html_content)
280
-
281
- # Parse and analyze URLs
282
- links = scout.extract_links(base_url='https://example.com')
283
- for link in links:
284
- url_components = scout.url_parse(link['href'])
285
- print(f"Domain: {url_components['netloc']}")
286
- print(f"Path: {url_components['path']}")
287
- ```
288
-
289
- ### Metadata Extraction
290
-
291
- ```python
292
- from webscout.scout import Scout
293
-
294
- scout = Scout(html_content)
295
-
296
- # Extract metadata
297
- metadata = scout.extract_metadata()
298
- print(f"Title: {metadata['title']}")
299
- print(f"Description: {metadata['description']}")
300
- print(f"Open Graph: {metadata['og_metadata']}")
301
- print(f"Twitter Card: {metadata['twitter_metadata']}")
302
- ```
303
-
304
- ### Content Hashing and Caching
305
-
306
- ```python
307
- from webscout.scout import Scout
308
-
309
- scout = Scout(html_content)
310
-
311
- # Generate content hash
312
- content_hash = scout.hash_content(method='sha256')
313
-
314
- # Use caching for expensive operations
315
- if not scout.cache('parsed_data'):
316
- data = scout.extract_semantic_info()
317
- scout.cache('parsed_data', data)
318
-
319
- cached_data = scout.cache('parsed_data')
320
- ```
321
-
322
- ## 📚 API Reference
323
-
324
- ### Core Classes
325
-
326
- | Class | Description |
327
- |-------|-------------|
328
- | `Scout` | Main class for HTML parsing and traversal |
329
- | `ScoutCrawler` | Web crawler for fetching and parsing multiple pages |
330
- | `ScoutTextAnalyzer` | Text analysis utilities |
331
- | `ScoutWebAnalyzer` | Web page analysis utilities |
332
- | `ScoutSearchResult` | Enhanced search results with filtering and analysis |
333
- | `Tag` | Represents an HTML/XML tag |
334
- | `NavigableString` | Represents text within an HTML/XML document |
335
-
336
- ### Key Methods
337
-
338
- #### Scout Class
339
-
340
- - `__init__(markup, features='html.parser', from_encoding=None)`: Initialize with HTML content
341
- - `find(name, attrs={}, recursive=True, text=None)`: Find first matching element
342
- - `find_all(name, attrs={}, recursive=True, text=None, limit=None)`: Find all matching elements
343
- - `select(selector)`: Find elements using CSS selector
344
- - `get_text(separator=' ', strip=False)`: Extract text from document
345
- - `analyze_text()`: Perform text analysis
346
- - `analyze_page_structure()`: Analyze document structure
347
- - `extract_semantic_info()`: Extract semantic information
348
- - `extract_links(base_url=None)`: Extract all links
349
- - `extract_metadata()`: Extract metadata from document
350
- - `to_json(indent=2)`: Convert to JSON
351
- - `to_markdown(heading_style='ATX')`: Convert to Markdown
352
- - `prettify(formatter='minimal')`: Pretty-print HTML
353
-
354
- #### ScoutCrawler Class
355
-
356
- - `__init__(base_url, max_pages=50, tags_to_remove=None)`: Initialize the crawler
357
- - `crawl()`: Start crawling from the base URL
358
- - `_crawl_page(url, depth=0)`: Crawl a single page (internal method)
359
- - `_is_valid_url(url)`: Check if a URL is valid (internal method)
360
-
361
- For detailed API documentation, please refer to the [documentation](https://github.com/OEvortex/Webscout/wiki).
362
-
363
- ## 🔧 Dependencies
364
-
365
- - `curl_cffi`: HTTP library used for web requests
366
- - `lxml`: XML and HTML processing library (optional, recommended)
367
- - `html5lib`: Standards-compliant HTML parser (optional)
368
- - `markdownify`: HTML to Markdown conversion
369
- - `concurrent.futures`: Asynchronous execution (standard library)
370
-
371
- ## 🌈 Supported Python Versions
372
-
373
- - Python 3.8+
374
-
375
- ## 🤝 Contributing
376
-
377
- Contributions are welcome! Here's how you can contribute:
378
-
379
- 1. Fork the repository
380
- 2. Create a feature branch (`git checkout -b feature/amazing-feature`)
381
- 3. Commit your changes (`git commit -m 'Add some amazing feature'`)
382
- 4. Push to the branch (`git push origin feature/amazing-feature`)
383
- 5. Open a Pull Request
384
-
385
- Please make sure to update tests as appropriate.
386
-
387
- ## 📄 License
388
-
389
- This project is licensed under the MIT License - see the LICENSE file for details.
390
-
391
- ---
392
-
393
- <div align="center">
394
- <p>Made with ❤️ by the Webscout team</p>
395
- <p>
396
- <a href="https://github.com/OEvortex/Webscout">GitHub</a> •
397
- <a href="https://github.com/OEvortex/Webscout/wiki">Documentation</a> •
398
- <a href="https://github.com/OEvortex/Webscout/issues">Report Bug</a> •
399
- <a href="https://github.com/OEvortex/Webscout/issues">Request Feature</a>
400
- </p>
401
- </div>
1
+ **🚀 The Most Advanced HTML Parser & Web Crawler for AI/LLM Data Collection**
2
+
3
+ **🌟 Built for the Future • Powered by Intelligence • Trusted by Developers**
4
+
5
+
6
+ ## 📋 Overview
7
+
8
+ Scout is an ultra-powerful, enterprise-grade HTML parsing and web crawling library designed for the AI era. Built with LLM data collection in mind, Scout provides unparalleled capabilities for extracting, analyzing, and processing web content at scale. With its BeautifulSoup-compatible API enhanced with modern features, Scout is the go-to solution for serious web scraping projects.
9
+
10
+ <details open>
11
+ <summary><b>🌟 Why Scout is the Ultimate Choice</b></summary>
12
+
13
+ - **🧠 LLM-Optimized Crawling**: Purpose-built for collecting high-quality training data for Large Language Models
14
+ - **🌐 Subdomain Intelligence**: Automatically discovers and crawls subdomains (e.g., blog.example.com, docs.example.com)
15
+ - **⚡ Lightning-Fast Performance**: Multi-threaded concurrent crawling with intelligent rate limiting
16
+ - **🎯 Surgical Precision**: Advanced content extraction that preserves structure while removing noise
17
+ - **🔍 Deep Analysis**: Built-in NLP capabilities for entity extraction, text analysis, and semantic understanding
18
+ - **🛡️ Enterprise-Ready**: Robust error handling, retry mechanisms, and respect for robots.txt
19
+ - **📊 Rich Data Extraction**: Captures metadata, structured data, semantic content, and more
20
+ - **🔄 Format Flexibility**: Export to JSON, Markdown, CSV, or custom formats
21
+ - **🎨 BeautifulSoup++ API**: Familiar interface with 10x more features
22
+
23
+ </details>
24
+
25
+ ## 📑 Table of Contents
26
+
27
+ - [Installation](#-installation)
28
+ - [Quick Start](#-quick-start)
29
+ - [Features](#-features)
30
+ - [Advanced Usage](#-advanced-usage)
31
+ - [API Reference](#-api-reference)
32
+ - [Dependencies](#-dependencies)
33
+ - [Supported Python Versions](#-supported-python-versions)
34
+ - [Contributing](#-contributing)
35
+ - [License](#-license)
36
+
37
+ ## 📦 Installation
38
+
39
+ ```bash
40
+ pip install webscout
41
+ ```
42
+
43
+ Or install the latest version from GitHub:
44
+
45
+ ```bash
46
+ pip install git+https://github.com/OEvortex/Webscout.git
47
+ ```
48
+
49
+ ## 🚀 Quick Start
50
+
51
+ ### Basic Parsing
52
+
53
+ ```python
54
+ from webscout.scout import Scout
55
+
56
+ # Parse HTML content
57
+ html_content = """
58
+ <html>
59
+ <body>
60
+ <h1>Hello, Scout!</h1>
61
+ <div class="content">
62
+ <p>Web parsing made easy.</p>
63
+ <a href="https://example.com">Link</a>
64
+ </div>
65
+ </body>
66
+ </html>
67
+ """
68
+
69
+ scout = Scout(html_content)
70
+
71
+ # Find elements
72
+ title = scout.find('h1')
73
+ links = scout.find_all('a')
74
+
75
+ # Extract text
76
+ print(title[0].get_text()) # Output: Hello, Scout!
77
+ print(links.attrs('href')) # Output: ['https://example.com']
78
+ ```
79
+
80
+ ### Web Crawling
81
+
82
+ ```python
83
+ from webscout.scout import ScoutCrawler
84
+
85
+ # Crawl a website with default settings
86
+ crawler = ScoutCrawler('https://example.com') # Default: max_pages=50
87
+
88
+ # Or customize the crawler
89
+ crawler = ScoutCrawler(
90
+ 'https://example.com', # base_url
91
+ max_pages=100, # maximum pages to crawl
92
+ tags_to_remove=['script', 'style', 'nav'] # tags to remove from content
93
+ )
94
+
95
+ # Start crawling
96
+ crawled_pages = crawler.crawl()
97
+
98
+ for page in crawled_pages:
99
+ print(f"URL: {page['url']}")
100
+ print(f"Title: {page['title']}")
101
+ print(f"Links found: {len(page['links'])}")
102
+ print(f"Crawl depth: {page['depth']}")
103
+ ```
104
+
105
+ ### Text Analysis
106
+
107
+ ```python
108
+ from webscout.scout import Scout
109
+
110
+ # Parse a webpage
111
+ html = """<div><h1>Climate Change</h1><p>Email us at info@example.com or call 555-123-4567.</p>
112
+ <p>Visit https://climate-action.org for more information.</p></div>"""
113
+ scout = Scout(html)
114
+
115
+ # Analyze text and extract entities
116
+ analysis = scout.analyze_text()
117
+ print(f"Word frequencies: {analysis['word_count']}")
118
+ print(f"Entities found: {analysis['entities']}")
119
+ ```
120
+
121
+ ## ✨ Features
122
+
123
+ ### 🔍 Multiple Parser Support
124
+
125
+ Scout supports multiple HTML/XML parsers, allowing you to choose the best tool for your specific needs:
126
+
127
+ | Parser | Description | Best For |
128
+ |--------|-------------|----------|
129
+ | `html.parser` | Python's built-in parser | General-purpose parsing, no dependencies |
130
+ | `lxml` | Fast C-based parser | Performance-critical applications |
131
+ | `html5lib` | Highly compliant HTML5 parser | Handling malformed HTML |
132
+ | `lxml-xml` | XML parser | XML document parsing |
133
+
134
+ ```python
135
+ # Choose your parser
136
+ scout = Scout(html_content, features='lxml') # For speed
137
+ scout = Scout(html_content, features='html5lib') # For compliance
138
+ ```
139
+
140
+ ### 🌐 Advanced Parsing Capabilities
141
+
142
+ Scout provides powerful tools for navigating and manipulating HTML/XML documents:
143
+
144
+ - **Element Selection**: Find elements by tag name, attributes, CSS selectors, and more
145
+ - **Tree Traversal**: Navigate parent-child relationships and sibling elements
146
+ - **Content Extraction**: Extract text, attributes, and structured data
147
+ - **Document Manipulation**: Modify, replace, or remove elements
148
+ - **Dynamic Building**: Easily append or insert new nodes
149
+
150
+ ```python
151
+ # CSS selector support
152
+ elements = scout.select('div.content > p')
153
+
154
+ # Advanced find with attribute matching
155
+ results = scout.find_all('a', attrs={'class': 'external', 'rel': 'nofollow'})
156
+
157
+ # Tree traversal
158
+ parent = element.find_parent('div')
159
+ siblings = element.find_next_siblings('p')
160
+ prev_sibling = element.find_previous_sibling('p')
161
+ ```
162
+
163
+ ### 🧠 Intelligent Analysis
164
+
165
+ Scout includes built-in analysis tools for extracting insights from web content:
166
+
167
+ #### Text Analysis
168
+
169
+ ```python
170
+ # Extract and analyze text
171
+ text = scout.get_text()
172
+ word_counts = scout.text_analyzer.count_words(text)
173
+ entities = scout.text_analyzer.extract_entities(text)
174
+ ```
175
+
176
+ #### Web Structure Analysis
177
+
178
+ ```python
179
+ # Analyze page structure
180
+ structure = scout.analyze_page_structure()
181
+ print(f"Most common tags: {structure['tag_distribution']}")
182
+ print(f"Page depth: {max(structure['depth_analysis'].keys())}")
183
+ ```
184
+
185
+ #### Semantic Information Extraction
186
+
187
+ ```python
188
+ # Extract semantic information
189
+ semantics = scout.extract_semantic_info()
190
+ print(f"Headings: {semantics['headings']}")
191
+ print(f"Lists: {len(semantics['lists']['ul']) + len(semantics['lists']['ol'])}")
192
+ print(f"Tables: {semantics['tables']['count']}")
193
+ ```
194
+
195
+ ### 🕸️ Web Crawling
196
+
197
+ Scout includes a powerful concurrent web crawler for fetching and analyzing multiple pages:
198
+
199
+ ```python
200
+ from webscout.scout import ScoutCrawler
201
+
202
+ # Create a crawler with default settings
203
+ crawler = ScoutCrawler('https://example.com') # Default: max_pages=50
204
+
205
+ # Or customize the crawler with specific options
206
+ crawler = ScoutCrawler(
207
+ 'https://example.com', # base_url
208
+ max_pages=100, # maximum pages to crawl
209
+ tags_to_remove=['script', 'style', 'nav'] # tags to remove from content
210
+ )
211
+
212
+ # Start crawling
213
+ pages = crawler.crawl()
214
+
215
+ # Process results
216
+ for page in pages:
217
+ print(f"URL: {page['url']}")
218
+ print(f"Title: {page['title']}")
219
+ print(f"Links: {len(page['links'])}")
220
+ print(f"Depth: {page['depth']}")
221
+ ```
222
+
223
+ The crawler automatically:
224
+ - Stays within the same domain as the base URL
225
+ - Uses concurrent requests for faster crawling
226
+ - Removes unwanted tags (like scripts and styles) for cleaner text extraction
227
+ - Tracks crawl depth for each page
228
+
229
+ ### 📄 Format Conversion
230
+
231
+ Scout can convert HTML to various formats:
232
+
233
+ ```python
234
+ # Convert to JSON
235
+ json_data = scout.to_json(indent=2)
236
+
237
+ # Convert to Markdown
238
+ markdown = scout.to_markdown(heading_style='ATX')
239
+
240
+ # Pretty-print HTML
241
+ pretty_html = scout.prettify()
242
+ ```
243
+
244
+ ## 🔬 Advanced Usage
245
+
246
+ ### Working with Search Results
247
+
248
+ Scout's search methods return a `ScoutSearchResult` object with powerful methods for processing results:
249
+
250
+ ```python
251
+ from webscout.scout import Scout
252
+
253
+ scout = Scout(html_content)
254
+
255
+ # Find all paragraphs
256
+ paragraphs = scout.find_all('p')
257
+
258
+ # Extract all text from results
259
+ all_text = paragraphs.texts(separator='\n')
260
+
261
+ # Extract specific attributes
262
+ hrefs = paragraphs.attrs('href')
263
+
264
+ # Filter results with a predicate function
265
+ important = paragraphs.filter(lambda p: 'important' in p.get('class', []))
266
+
267
+ # Transform results
268
+ word_counts = paragraphs.map(lambda p: len(p.get_text().split()))
269
+
270
+ # Analyze text in results
271
+ analysis = paragraphs.analyze_text()
272
+ ```
273
+
274
+ ### URL Handling and Analysis
275
+
276
+ ```python
277
+ from webscout.scout import Scout
278
+
279
+ scout = Scout(html_content)
280
+
281
+ # Parse and analyze URLs
282
+ links = scout.extract_links(base_url='https://example.com')
283
+ for link in links:
284
+ url_components = scout.url_parse(link['href'])
285
+ print(f"Domain: {url_components['netloc']}")
286
+ print(f"Path: {url_components['path']}")
287
+ ```
288
+
289
+ ### Metadata Extraction
290
+
291
+ ```python
292
+ from webscout.scout import Scout
293
+
294
+ scout = Scout(html_content)
295
+
296
+ # Extract metadata
297
+ metadata = scout.extract_metadata()
298
+ print(f"Title: {metadata['title']}")
299
+ print(f"Description: {metadata['description']}")
300
+ print(f"Open Graph: {metadata['og_metadata']}")
301
+ print(f"Twitter Card: {metadata['twitter_metadata']}")
302
+ ```
303
+
304
+ ### Content Hashing and Caching
305
+
306
+ ```python
307
+ from webscout.scout import Scout
308
+
309
+ scout = Scout(html_content)
310
+
311
+ # Generate content hash
312
+ content_hash = scout.hash_content(method='sha256')
313
+
314
+ # Use caching for expensive operations
315
+ if not scout.cache('parsed_data'):
316
+ data = scout.extract_semantic_info()
317
+ scout.cache('parsed_data', data)
318
+
319
+ cached_data = scout.cache('parsed_data')
320
+ ```
321
+
322
+ ## 📚 API Reference
323
+
324
+ ### Core Classes
325
+
326
+ | Class | Description |
327
+ |-------|-------------|
328
+ | `Scout` | Main class for HTML parsing and traversal |
329
+ | `ScoutCrawler` | Web crawler for fetching and parsing multiple pages |
330
+ | `ScoutTextAnalyzer` | Text analysis utilities |
331
+ | `ScoutWebAnalyzer` | Web page analysis utilities |
332
+ | `ScoutSearchResult` | Enhanced search results with filtering and analysis |
333
+ | `Tag` | Represents an HTML/XML tag |
334
+ | `NavigableString` | Represents text within an HTML/XML document |
335
+
336
+ ### Key Methods
337
+
338
+ #### Scout Class
339
+
340
+ - `__init__(markup, features='html.parser', from_encoding=None)`: Initialize with HTML content
341
+ - `find(name, attrs={}, recursive=True, text=None)`: Find first matching element
342
+ - `find_all(name, attrs={}, recursive=True, text=None, limit=None)`: Find all matching elements
343
+ - `select(selector)`: Find elements using CSS selector
344
+ - `get_text(separator=' ', strip=False)`: Extract text from document
345
+ - `analyze_text()`: Perform text analysis
346
+ - `analyze_page_structure()`: Analyze document structure
347
+ - `extract_semantic_info()`: Extract semantic information
348
+ - `extract_links(base_url=None)`: Extract all links
349
+ - `extract_metadata()`: Extract metadata from document
350
+ - `to_json(indent=2)`: Convert to JSON
351
+ - `to_markdown(heading_style='ATX')`: Convert to Markdown
352
+ - `prettify(formatter='minimal')`: Pretty-print HTML
353
+
354
+ #### ScoutCrawler Class
355
+
356
+ - `__init__(base_url, max_pages=50, tags_to_remove=None)`: Initialize the crawler
357
+ - `crawl()`: Start crawling from the base URL
358
+ - `_crawl_page(url, depth=0)`: Crawl a single page (internal method)
359
+ - `_is_valid_url(url)`: Check if a URL is valid (internal method)
360
+
361
+ For detailed API documentation, please refer to the [documentation](https://github.com/OEvortex/Webscout/wiki).
362
+
363
+ ## 🔧 Dependencies
364
+
365
+ - `curl_cffi`: HTTP library used for web requests
366
+ - `lxml`: XML and HTML processing library (optional, recommended)
367
+ - `html5lib`: Standards-compliant HTML parser (optional)
368
+ - `markdownify`: HTML to Markdown conversion
369
+ - `concurrent.futures`: Asynchronous execution (standard library)
370
+
371
+ ## 🌈 Supported Python Versions
372
+
373
+ - Python 3.8+
374
+
375
+ ## 🤝 Contributing
376
+
377
+ Contributions are welcome! Here's how you can contribute:
378
+
379
+ 1. Fork the repository
380
+ 2. Create a feature branch (`git checkout -b feature/amazing-feature`)
381
+ 3. Commit your changes (`git commit -m 'Add some amazing feature'`)
382
+ 4. Push to the branch (`git push origin feature/amazing-feature`)
383
+ 5. Open a Pull Request
384
+
385
+ Please make sure to update tests as appropriate.
386
+
387
+ ## 📄 License
388
+
389
+ This project is licensed under the MIT License - see the LICENSE file for details.
390
+
391
+ ---
392
+
393
+ <div align="center">
394
+ <p>Made with ❤️ by the Webscout team</p>
395
+ <p>
396
+ <a href="https://github.com/OEvortex/Webscout">GitHub</a> •
397
+ <a href="https://github.com/OEvortex/Webscout/wiki">Documentation</a> •
398
+ <a href="https://github.com/OEvortex/Webscout/issues">Report Bug</a> •
399
+ <a href="https://github.com/OEvortex/Webscout/issues">Request Feature</a>
400
+ </p>
401
+ </div>