h-ai-brain 0.0.3__py3-none-any.whl → 0.0.5__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.
@@ -23,6 +23,7 @@ class WebDocsService:
23
23
  async def discover_documentation(self, website_url: str) -> Optional[List[TextPage]]:
24
24
  detected_links = await self.detect_documentation_links(website_url)
25
25
  for link in detected_links:
26
+ print(f"Fetching {link.url}")
26
27
  gitbook_fetcher = GitbookWebFetcherService(link.url)
27
28
  gitbook_pages = await gitbook_fetcher.fetch()
28
29
  return gitbook_pages
@@ -16,6 +16,8 @@ class WebDocsLinkDetector:
16
16
  doc_links = []
17
17
 
18
18
  web_content = await self.web_fetcher.fetch(website_url)
19
+ if not web_content:
20
+ return doc_links
19
21
 
20
22
  soup_processor = SoupProcessor(web_content)
21
23
  web_links = soup_processor.extract_links(website_url)
@@ -14,12 +14,15 @@ class PlayWrightWebContentFetcher(WebFetcherRepository):
14
14
  'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
15
15
  'Accept-Language': 'en-US,en;q=0.5'
16
16
  }
17
- self.page_load_timeout = 30
17
+ self.page_load_timeout = 60
18
18
  self.wait_for_idle = True
19
19
 
20
20
  async def fetch(self, url: str) -> Optional[str]:
21
21
  async with async_playwright() as p:
22
- browser = await p.chromium.launch()
22
+ browser = await p.chromium.launch(headless=True)
23
+ logger.debug(
24
+ f"Launching headless browser with user agent: {self.headers.get('User-Agent')}"
25
+ )
23
26
  try:
24
27
  context = await browser.new_context(
25
28
  user_agent=self.headers.get('User-Agent')
@@ -29,12 +32,19 @@ class PlayWrightWebContentFetcher(WebFetcherRepository):
29
32
  # Set timeout
30
33
  page.set_default_timeout(self.page_load_timeout * 1000) # Convert to ms
31
34
 
35
+ page.on("console", lambda msg: logger.debug(f"Browser console {url}: {msg.text}"))
36
+
32
37
  # Navigate to the URL
33
- await page.goto(url)
38
+ await page.goto(url, timeout=self.page_load_timeout * 1000, wait_until='domcontentloaded')
34
39
 
35
40
  # Wait for network to be idle if requested
36
41
  if self.wait_for_idle:
37
- await page.wait_for_load_state("networkidle")
42
+ logger.debug(f"Waiting for network idle on {url}")
43
+
44
+ await page.wait_for_load_state("networkidle", timeout=self.page_load_timeout * 1000)
45
+ logger.debug(
46
+ f"Network idle on {url} after {self.page_load_timeout} seconds"
47
+ )
38
48
 
39
49
  logger.debug(f"Successfully fetched {url} with headless browser")
40
50
 
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: h_ai_brain
3
- Version: 0.0.3
3
+ Version: 0.0.5
4
4
  Summary: AI Research agent API
5
5
  Author-email: shoebill <shoebill.hai@gmail.com>
6
6
  Classifier: Programming Language :: Python :: 3
@@ -1,7 +1,7 @@
1
1
  h_ai/__init__.py,sha256=bmHMDoui52Q73UvXdHslQ3w_LubmhRuKRlrjOYyCP8c,153
2
2
  h_ai/application/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
3
3
  h_ai/application/hai_service.py,sha256=DpSx1_QYS_3N5OwY5U4My0WwH-e4tvRHNeJxSduGoZM,2200
4
- h_ai/application/web_docs_service.py,sha256=45Pxhm279pGm3xWx00qOrS5pFjLHrbZTEhHTVXqyxJQ,1609
4
+ h_ai/application/web_docs_service.py,sha256=YiPBfPyjlloDq6CIOP0u7F1jNBK-elYRU8xl4qJ1oVc,1652
5
5
  h_ai/application/system_prompts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
6
6
  h_ai/application/system_prompts/roles/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
7
7
  h_ai/domain/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -15,7 +15,7 @@ h_ai/domain/web_docs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hS
15
15
  h_ai/domain/web_docs/doc_link_scorer_service.py,sha256=EmLSOaX7BCUQcKHZquaUt-Ps_DssZrRqpch5MgbUhAc,1444
16
16
  h_ai/domain/web_docs/documentation_pattern_repository.py,sha256=VhNzP3PUqgg9MaWhBVefj13XNxRBh6ZPUt-KH70ww2w,1302
17
17
  h_ai/domain/web_docs/gitbook_web_fetcher_service.py,sha256=Ye-TcuwgW1fhIY8x6v9_-pmPN9pVFWzlOpwRt-4teaA,6490
18
- h_ai/domain/web_docs/web_docs_link_detector.py,sha256=ePiIvMfT0fLiQNKEeZeU_MaATL568DtiajYUETwbn10,1133
18
+ h_ai/domain/web_docs/web_docs_link_detector.py,sha256=NyMKFNs-41bqrxx6u-9GqIufy7pkDF_-_f1h8HECBK8,1192
19
19
  h_ai/domain/web_docs/web_link.py,sha256=J4KC3MmjkvWlAPDdEdjcqAZCvuSnJMahudCohiBk3wk,307
20
20
  h_ai/domain/web_docs/gitbook/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
21
21
  h_ai/domain/web_docs/gitbook/text_chapter.py,sha256=XiZZlt128uA6oq-4bQfOpFf-djoHiQEsWpFDzRCNXdk,534
@@ -39,10 +39,10 @@ h_ai/infrastructure/llm/ollama/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCe
39
39
  h_ai/infrastructure/llm/ollama/models/ollama_chat_message.py,sha256=ZIz4PQ3869vI3xAYYufPrxXpacajRDtOI8RDl5Dm9RQ,305
40
40
  h_ai/infrastructure/llm/ollama/models/ollama_chat_session.py,sha256=GZ_ddpbWa8iy6NZq50vokUFVZBiX0WNa81z9-r9RzTY,392
41
41
  h_ai/infrastructure/playwright/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
42
- h_ai/infrastructure/playwright/playwright_web_content_fetcher.py,sha256=DHXkx91SP55PUT_o3ED1Z6uB0ijN-DeTXCnxdnXkDFw,1817
43
- h_ai_brain-0.0.3.dist-info/licenses/LICENSE,sha256=SbvpEU5JIU3yzMMkyzrI0dGqHDoJR_lMKGdl6GZHsy4,11558
44
- h_ai_brain-0.0.3.dist-info/licenses/NOTICE.txt,sha256=vxeIKUiGqAePLvDW4AVm3Xh-3BcsvMtCMn1tbsr9zsE,668
45
- h_ai_brain-0.0.3.dist-info/METADATA,sha256=Xdn_wNKqOOU1fpqiyST5Yu83gWqBSj1R8cZ6VJuIufA,735
46
- h_ai_brain-0.0.3.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
47
- h_ai_brain-0.0.3.dist-info/top_level.txt,sha256=3MChDBWvDJV4cEHuZhzeODxQ4ewtw-arOuyaDOc6sIo,5
48
- h_ai_brain-0.0.3.dist-info/RECORD,,
42
+ h_ai/infrastructure/playwright/playwright_web_content_fetcher.py,sha256=fcf8ZxIR2bLU1rV378ASQUaI26PvaX7sYqQb1SDlkt4,2401
43
+ h_ai_brain-0.0.5.dist-info/licenses/LICENSE,sha256=SbvpEU5JIU3yzMMkyzrI0dGqHDoJR_lMKGdl6GZHsy4,11558
44
+ h_ai_brain-0.0.5.dist-info/licenses/NOTICE.txt,sha256=vxeIKUiGqAePLvDW4AVm3Xh-3BcsvMtCMn1tbsr9zsE,668
45
+ h_ai_brain-0.0.5.dist-info/METADATA,sha256=d6J1f3gTeJaS90RwHDfPLuwPila1TzYFxbRInOqHqHM,735
46
+ h_ai_brain-0.0.5.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
47
+ h_ai_brain-0.0.5.dist-info/top_level.txt,sha256=3MChDBWvDJV4cEHuZhzeODxQ4ewtw-arOuyaDOc6sIo,5
48
+ h_ai_brain-0.0.5.dist-info/RECORD,,