docs2epub 0.1.6__py3-none-any.whl → 0.1.8__py3-none-any.whl

docs2epub/docusaurus_next.py

@@ -85,9 +85,46 @@ def _extract_article(soup: BeautifulSoup) -> Tag:
   role_main = soup.find(attrs={"role": "main"})
   if role_main:
     return role_main
+  for selector in [
+    "div#content",
+    "div.content",
+    "div#main",
+    "div.main",
+    "div#page",
+    "div.page",
+    "div.document",
+    "div#document",
+  ]:
+    candidate = soup.select_one(selector)
+    if candidate:
+      return candidate
+  body = soup.find("body")
+  if body:
+    return body
   raise RuntimeError("Could not find <article> in page HTML")
 
 
+def _extract_canonical_url(soup: BeautifulSoup, *, base_url: str) -> str | None:
+  for link in soup.find_all("link", href=True, rel=True):
+    rel = link.get("rel")
+    rel_values = []
+    if isinstance(rel, list):
+      rel_values = [str(r).lower() for r in rel]
+    else:
+      rel_values = [str(rel).lower()]
+    if "canonical" not in rel_values:
+      continue
+    href = str(link.get("href") or "").strip()
+    if not href:
+      continue
+    canonical = urljoin(base_url, href)
+    parsed = urlparse(canonical)
+    if parsed.scheme not in ("http", "https"):
+      continue
+    return canonical
+  return None
+
+
 def _canonicalize_url(url: str) -> str:
   parsed = urlparse(url)
   path = parsed.path or "/"
@@ -321,6 +358,17 @@ def iter_docusaurus_next(options: DocusaurusNextOptions) -> list[Chapter]:
     return BeautifulSoup(resp.text, "lxml")
 
   initial_soup = fetch_soup(url)
+  canonical = _extract_canonical_url(initial_soup, base_url=url)
+  if options.base_url is None and canonical:
+    start_origin = urlparse(url).netloc.lower()
+    canonical_origin = urlparse(canonical).netloc.lower()
+    if canonical_origin == start_origin:
+      canonical_key = _canonicalize_url(canonical)
+      if canonical_key != _canonicalize_url(url):
+        url = canonical
+        base_url = canonical
+        initial_soup = fetch_soup(url)
+
   sidebar_urls = _extract_sidebar_urls(initial_soup, base_url=base_url, start_url=url)
   initial_key = _canonicalize_url(url)
 
@@ -342,13 +390,22 @@ def iter_docusaurus_next(options: DocusaurusNextOptions) -> list[Chapter]:
           return None
         raise
 
-    article = _extract_article(page_soup)
+    try:
+      article = _extract_article(page_soup)
+    except RuntimeError:
+      if key != initial_key:
+        return None
+      raise
     title_el = article.find(["h1", "h2"])
     title = (
       " ".join(title_el.get_text(" ", strip=True).split())
       if title_el
       else f"Chapter {len(chapters) + 1}"
     )
+    if title_el is None and article.name == "body":
+      body_text = " ".join(article.get_text(" ", strip=True).split())
+      if len(body_text) < 200:
+        return None
 
     _remove_unwanted(article)
     _absolutize_urls(article, base_url=target_url)

{docs2epub-0.1.6.dist-info → docs2epub-0.1.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docs2epub
-Version: 0.1.6
+Version: 0.1.8
 Summary: Turn documentation sites into an EPUB (Kindle-friendly).
 Author: Breno Brito
 License: MIT

{docs2epub-0.1.6.dist-info → docs2epub-0.1.8.dist-info}/RECORD

@@ -1,11 +1,11 @@
 docs2epub/__init__.py,sha256=iccyEu4zlubhvd6pM7Z2Gjwn8tPw9IhZ4ABKhbiFjUY,54
 docs2epub/cli.py,sha256=pt1crvrkr2k1ybf_p0m4xSYyoZVluFsDNGuwJ7CykYM,3863
-docs2epub/docusaurus_next.py,sha256=c4EZMo7E6zeuekbA3n_rF1joT3Km1cPY1HTimzUkMFg,10866
+docs2epub/docusaurus_next.py,sha256=nQYkNecXgh4TsxaTydoiC1tVmIqjYiLiyEtYlpXGmXg,12507
 docs2epub/epub.py,sha256=OsPWcPGTgazAeNpWASIE6e4HQ5ILQr2VFO1-Aj3y1kg,2986
 docs2epub/kindle_html.py,sha256=LN0CGj9ap9b8iC_MlZcQLuhJ7FehZr_VbIfMOz78E5c,2297
 docs2epub/model.py,sha256=uL7uwbG6yU0bEGpSFxxIv2pcZHQR9cs2prfqk5iNQwc,160
 docs2epub/pandoc_epub2.py,sha256=l22-QAQcCgJyl7HF0_b5weC3qEGVQLwOhxdbAvd8C2o,3610
-docs2epub-0.1.6.dist-info/METADATA,sha256=Qu_OyYWfevaG_y7rCpUR81AT8aYK9Yo9KS4Cz_ZgDg8,1886
-docs2epub-0.1.6.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-docs2epub-0.1.6.dist-info/entry_points.txt,sha256=DHK4mzthrIXUvM8Y8Vo_3jG2IhegEDDM7T9CvCkUtvw,49
-docs2epub-0.1.6.dist-info/RECORD,,
+docs2epub-0.1.8.dist-info/METADATA,sha256=KdwbHGiBRLuXLQKlTypnDH8eOogD5bDoSGDIJgNriZs,1886
+docs2epub-0.1.8.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+docs2epub-0.1.8.dist-info/entry_points.txt,sha256=DHK4mzthrIXUvM8Y8Vo_3jG2IhegEDDM7T9CvCkUtvw,49
+docs2epub-0.1.8.dist-info/RECORD,,