markdown-extractor 0.1.0__py3-none-any.whl

markdown_extractor-0.1.0.dist-info/METADATA

@@ -0,0 +1,676 @@
+Metadata-Version: 2.4
+Name: markdown-extractor
+Version: 0.1.0
+Summary: Extract structured sections from Markdown by header — bracket-style access with robust handling of code blocks, tables, math, and YAML front matter.
+Author-email: Fasil <fasilwdr@hotmail.com>
+License: Apache License
+                                   Version 2.0, January 2004
+                                http://www.apache.org/licenses/
+        
+           TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+        
+           1. Definitions.
+        
+              "License" shall mean the terms and conditions for use, reproduction,
+              and distribution as defined by Sections 1 through 9 of this document.
+        
+              "Licensor" shall mean the copyright owner or entity authorized by
+              the copyright owner that is granting the License.
+        
+              "Legal Entity" shall mean the union of the acting entity and all
+              other entities that control, are controlled by, or are under common
+              control with that entity. For the purposes of this definition,
+              "control" means (i) the power, direct or indirect, to cause the
+              direction or management of such entity, whether by contract or
+              otherwise, or (ii) ownership of fifty percent (50%) or more of the
+              outstanding shares, or (iii) beneficial ownership of such entity.
+        
+              "You" (or "Your") shall mean an individual or Legal Entity
+              exercising permissions granted by this License.
+        
+              "Source" form shall mean the preferred form for making modifications,
+              including but not limited to software source code, documentation
+              source, and configuration files.
+        
+              "Object" form shall mean any form resulting from mechanical
+              transformation or translation of a Source form, including but
+              not limited to compiled object code, generated documentation,
+              and conversions to other media types.
+        
+              "Work" shall mean the work of authorship, whether in Source or
+              Object form, made available under the License, as indicated by a
+              copyright notice that is included in or attached to the work
+              (an example is provided in the Appendix below).
+        
+              "Derivative Works" shall mean any work, whether in Source or Object
+              form, that is based on (or derived from) the Work and for which the
+              editorial revisions, annotations, elaborations, or other modifications
+              represent, as a whole, an original work of authorship. For the purposes
+              of this License, Derivative Works shall not include works that remain
+              separable from, or merely link (or bind by name) to the interfaces of,
+              the Work and Derivative Works thereof.
+        
+              "Contribution" shall mean any work of authorship, including
+              the original version of the Work and any modifications or additions
+              to that Work or Derivative Works thereof, that is intentionally
+              submitted to Licensor for inclusion in the Work by the copyright owner
+              or by an individual or Legal Entity authorized to submit on behalf of
+              the copyright owner. For the purposes of this definition, "submitted"
+              means any form of electronic, verbal, or written communication sent
+              to the Licensor or its representatives, including but not limited to
+              communication on electronic mailing lists, source code control systems,
+              and issue tracking systems that are managed by, or on behalf of, the
+              Licensor for the purpose of discussing and improving the Work, but
+              excluding communication that is conspicuously marked or otherwise
+              designated in writing by the copyright owner as "Not a Contribution."
+        
+              "Contributor" shall mean Licensor and any individual or Legal Entity
+              on behalf of whom a Contribution has been received by Licensor and
+              subsequently incorporated within the Work.
+        
+           2. Grant of Copyright License. Subject to the terms and conditions of
+              this License, each Contributor hereby grants to You a perpetual,
+              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+              copyright license to reproduce, prepare Derivative Works of,
+              publicly display, publicly perform, sublicense, and distribute the
+              Work and such Derivative Works in Source or Object form.
+        
+           3. Grant of Patent License. Subject to the terms and conditions of
+              this License, each Contributor hereby grants to You a perpetual,
+              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+              (except as stated in this section) patent license to make, have made,
+              use, offer to sell, sell, import, and otherwise transfer the Work,
+              where such license applies only to those patent claims licensable
+              by such Contributor that are necessarily infringed by their
+              Contribution(s) alone or by combination of their Contribution(s)
+              with the Work to which such Contribution(s) was submitted. If You
+              institute patent litigation against any entity (including a
+              cross-claim or counterclaim in a lawsuit) alleging that the Work
+              or a Contribution incorporated within the Work constitutes direct
+              or contributory patent infringement, then any patent licenses
+              granted to You under this License for that Work shall terminate
+              as of the date such litigation is filed.
+        
+           4. Redistribution. You may reproduce and distribute copies of the
+              Work or Derivative Works thereof in any medium, with or without
+              modifications, and in Source or Object form, provided that You
+              meet the following conditions:
+        
+              (a) You must give any other recipients of the Work or
+                  Derivative Works a copy of this License; and
+        
+              (b) You must cause any modified files to carry prominent notices
+                  stating that You changed the files; and
+        
+              (c) You must retain, in the Source form of any Derivative Works
+                  that You distribute, all copyright, patent, trademark, and
+                  attribution notices from the Source form of the Work,
+                  excluding those notices that do not pertain to any part of
+                  the Derivative Works; and
+        
+              (d) If the Work includes a "NOTICE" text file as part of its
+                  distribution, then any Derivative Works that You distribute must
+                  include a readable copy of the attribution notices contained
+                  within such NOTICE file, excluding those notices that do not
+                  pertain to any part of the Derivative Works, in at least one
+                  of the following places: within a NOTICE text file distributed
+                  as part of the Derivative Works; within the Source form or
+                  documentation, if provided along with the Derivative Works; or,
+                  within a display generated by the Derivative Works, if and
+                  wherever such third-party notices normally appear. The contents
+                  of the NOTICE file are for informational purposes only and
+                  do not modify the License. You may add Your own attribution
+                  notices within Derivative Works that You distribute, alongside
+                  or as an addendum to the NOTICE text from the Work, provided
+                  that such additional attribution notices cannot be construed
+                  as modifying the License.
+        
+              You may add Your own copyright statement to Your modifications and
+              may provide additional or different license terms and conditions
+              for use, reproduction, or distribution of Your modifications, or
+              for any such Derivative Works as a whole, provided Your use,
+              reproduction, and distribution of the Work otherwise complies with
+              the conditions stated in this License.
+        
+           5. Submission of Contributions. Unless You explicitly state otherwise,
+              any Contribution intentionally submitted for inclusion in the Work
+              by You to the Licensor shall be under the terms and conditions of
+              this License, without any additional terms or conditions.
+              Notwithstanding the above, nothing herein shall supersede or modify
+              the terms of any separate license agreement you may have executed
+              with Licensor regarding such Contributions.
+        
+           6. Trademarks. This License does not grant permission to use the trade
+              names, trademarks, service marks, or product names of the Licensor,
+              except as required for reasonable and customary use in describing the
+              origin of the Work and reproducing the content of the NOTICE file.
+        
+           7. Disclaimer of Warranty. Unless required by applicable law or
+              agreed to in writing, Licensor provides the Work (and each
+              Contributor provides its Contributions) on an "AS IS" BASIS,
+              WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+              implied, including, without limitation, any warranties or conditions
+              of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+              PARTICULAR PURPOSE. You are solely responsible for determining the
+              appropriateness of using or redistributing the Work and assume any
+              risks associated with Your exercise of permissions under this License.
+        
+           8. Limitation of Liability. In no event and under no legal theory,
+              whether in tort (including negligence), contract, or otherwise,
+              unless required by applicable law (such as deliberate and grossly
+              negligent acts) or agreed to in writing, shall any Contributor be
+              liable to You for damages, including any direct, indirect, special,
+              incidental, or consequential damages of any character arising as a
+              result of this License or out of the use or inability to use the
+              Work (including but not limited to damages for loss of goodwill,
+              work stoppage, computer failure or malfunction, or any and all
+              other commercial damages or losses), even if such Contributor
+              has been advised of the possibility of such damages.
+        
+           9. Accepting Warranty or Additional Liability. While redistributing
+              the Work or Derivative Works thereof, You may choose to offer,
+              and charge a fee for, acceptance of support, warranty, indemnity,
+              or other liability obligations and/or rights consistent with this
+              License. However, in accepting such obligations, You may act only
+              on Your own behalf and on Your sole responsibility, not on behalf
+              of any other Contributor, and only if You agree to indemnify,
+              defend, and hold each Contributor harmless for any liability
+              incurred by, or claims asserted against, such Contributor by reason
+              of your accepting any such warranty or additional liability.
+        
+           END OF TERMS AND CONDITIONS
+        
+           APPENDIX: How to apply the Apache License to your work.
+        
+              To apply the Apache License to your work, attach the following
+              boilerplate notice, with the fields enclosed by brackets "[]"
+              replaced with your own identifying information. (Don't include
+              the brackets!)  The text should be enclosed in the appropriate
+              comment syntax for the file format. We also recommend that a
+              file or class name and description of purpose be included on the
+              same "printed page" as the copyright notice for easier
+              identification within third-party archives.
+        
+           Copyright [yyyy] [name of copyright owner]
+        
+           Licensed under the Apache License, Version 2.0 (the "License");
+           you may not use this file except in compliance with the License.
+           You may obtain a copy of the License at
+        
+               http://www.apache.org/licenses/LICENSE-2.0
+        
+           Unless required by applicable law or agreed to in writing, software
+           distributed under the License is distributed on an "AS IS" BASIS,
+           WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+           See the License for the specific language governing permissions and
+           limitations under the License.
+        
+Project-URL: Homepage, https://github.com/fasilwdr/MD-Extractor
+Project-URL: Documentation, https://github.com/fasilwdr/MD-Extractor#readme
+Project-URL: Source, https://github.com/fasilwdr/MD-Extractor
+Project-URL: Issues, https://github.com/fasilwdr/MD-Extractor/issues
+Project-URL: Changelog, https://github.com/fasilwdr/MD-Extractor/releases
+Keywords: markdown,parser,extractor,headers,sections,ast
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Text Processing :: Markup :: Markdown
+Classifier: Typing :: Typed
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Provides-Extra: dev
+Requires-Dist: pytest>=7; extra == "dev"
+Requires-Dist: lxml>=4.9; extra == "dev"
+Requires-Dist: build; extra == "dev"
+Requires-Dist: twine; extra == "dev"
+Provides-Extra: xpath
+Requires-Dist: lxml>=4.9; extra == "xpath"
+Dynamic: license-file
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/fasilwdr/MD-Extractor/main/assets/markdown-extractor.svg" alt="markdown-extractor logo">
+</p>
+
+# markdown-extractor
+
+Turn a Markdown document into a navigable tree of sections keyed by header,
+then drop into the body of any section to get its blocks, plain text, JSON,
+or HTML — with optional XPath filtering.
+
+- **Header tree** — bracket access, recursive search, ASCII tree.
+- **Block tree** — paragraphs, ordered/unordered lists with nesting, code
+  fences, blockquotes — parsed lazily per section.
+- **Renderers** — `to_list()`, `to_dict()`, `to_json()`, `to_html()`,
+  `to_text()`, all on both `MDExtractor` and any `Section`.
+- **Robust parsing** — headers inside code blocks, tables, math blocks, and
+  YAML front matter are correctly ignored.
+- **Zero runtime dependencies** for everything except XPath (opt-in extra).
+- **Pure Python**, `>= 3.8`. Lazy slicing — large documents stay cheap.
+
+---
+
+## Installation
+
+```bash
+pip install markdown-extractor
+```
+
+For XPath support on `to_html()`:
+
+```bash
+pip install markdown-extractor[xpath]
+```
+
+From a local checkout:
+
+```bash
+pip install -e .
+```
+
+---
+
+## Quick start
+
+```python
+from markdown_extractor import MDExtractor
+
+md = """
+# Section 1
+Some content here.
+
+- **Lightweight** — small footprint.
+- *Flexible* — extensible by design.
+- `Tested` — full coverage.
+
+## Subsection 1.1
+More details.
+
+## FAQ
+- **Which versions are supported?**
+
+    Versions 1.0 and up.
+- **Where do I report bugs?**
+
+    Open an issue on GitHub.
+"""
+
+e = MDExtractor(md)
+
+e["Section 1"]                       # bracket access by title
+e["Section 1"]["Subsection 1.1"]     # nested
+e.get("Section 1", "Subsection 1.1") # multi-step (soft — see below)
+e.list()                             # ['Section 1']
+e[""]                                # synthetic root: the whole document
+```
+
+Every example below uses this same `md`. Load straight from disk instead:
+
+```python
+e = MDExtractor.from_file("docs/guide.md")
+```
+
+---
+
+## Navigating the header tree
+
+### Strict access — `[]` / `get_section()`
+
+```python
+e["Section 1"]                          # KeyError if missing
+e.get_section("Section 1", "Sub 1.1")   # KeyError if any title is missing
+"Section 1" in e
+```
+
+### Soft access — `get()`
+
+`get()` walks the same path but returns a **null section sentinel** instead
+of raising when something is missing. The sentinel is falsy and its
+renderer methods all return empty values, so chains stay safe:
+
+```python
+e.get("Section 1", "Subsection 1.1").to_list()   # works
+e.get("Nope", "Anything").to_list()              # []  — no exception
+e.get("Nope").to_html()                          # ""
+e.get("Nope").to_dict()                          # {'title':'', 'level':0, ...}
+
+if not e.get("Optional Section"):
+    print("section absent")
+```
+
+Use `[]`/`get_section()` when you want missing keys to fail loudly; use
+`get()` when you want to flow through to an empty result.
+
+### Discovery
+
+```python
+e.list()                              # immediate child titles
+e["Section 1"].list()                 # children of "Section 1"
+e.find("Subsection 1.1")              # every section with that title
+e.walk()                              # depth-first iterator over every header
+e.tree()                              # ASCII tree of the whole document
+```
+
+---
+
+## Reading a section's body
+
+Every `Section` parses its own body lazily into a tree of blocks
+(paragraphs / lists / list items / code / blockquote). This view is what
+powers `to_list`, `to_dict`, `to_html`, and `to_text`.
+
+```python
+s = e["Section 1"]
+
+s.blocks       # the parsed Block tree (lazy, cached)
+s.text         # raw prose, no header line, no subsections
+s.body         # raw prose + nested subsections
+s.content      # the full slice including the header line
+```
+
+### Reaching a single block — `block()` and `text_plain`
+
+When you've isolated a single piece of text inside the block tree,
+`Block.text_plain` strips the inline Markdown markers so you don't have
+to round-trip through `to_text()`:
+
+```python
+s.blocks[1].children[1].text          # '*Flexible* — extensible by design.'
+s.blocks[1].children[1].text_plain    # 'Flexible — extensible by design.'
+```
+
+`block.text` is kept raw on purpose — `to_dict()` / `to_json()` is a
+lossless round-trip of the source. `text_plain` is the on-demand
+plain-text view.
+
+For chains that might break (a missing list item, an empty section),
+use `Section.block(*indices)` and `Block.get(*indices)`. These return
+a *null Block* on out-of-range indices instead of raising
+`IndexError` — so the chain stays safe end-to-end:
+
+```python
+s.block(1, 1).text_plain            # 'Flexible — extensible by design.'
+s.block(99, 99).text_plain          # ''  — no exception
+
+# Equivalent two-step form (block() walks .blocks; .get() walks .children):
+s.block(1).get(1).text_plain
+
+bool(s.block(99))                   # False — null sentinel
+```
+
+`section.blocks[i]` / `block.children[j]` keep raising `IndexError` on
+out-of-range — strict access stays strict. Use `block()` / `.get()` only
+when you want soft fall-through.
+
+### `to_list()` — flatten body to strings
+
+One entry per top-level block. Lists expand to one entry per top-level
+item; `text` is preserved raw (use `text_plain` per-item if you want
+markers stripped):
+
+```python
+s.to_list()
+# ['Some content here.',
+#  '**Lightweight** — small footprint.',
+#  '*Flexible* — extensible by design.',
+#  '`Tested` — full coverage.']
+```
+
+### `to_dict()` / `to_json()` — full structured output
+
+Header subsections live under `children`; the body block tree lives under
+`blocks`. Indented continuation paragraphs under a bullet (FAQ-style)
+are attached as that bullet's `children`:
+
+```python
+e["Section 1"]["FAQ"].to_dict()
+# {
+#   "title": "FAQ",
+#   "level": 2,
+#   "text": "...",
+#   "blocks": [
+#     {"kind": "list", "text": "", "children": [
+#       {"kind": "list_item",
+#        "text": "**Which versions are supported?**",
+#        "children": [
+#          {"kind": "paragraph", "text": "Versions 1.0 and up."}
+#        ]},
+#       {"kind": "list_item",
+#        "text": "**Where do I report bugs?**",
+#        "children": [
+#          {"kind": "paragraph", "text": "Open an issue on GitHub."}
+#        ]}
+#     ]}
+#   ],
+#   "children": []
+# }
+
+e["Section 1"]["FAQ"].to_json(indent=2)
+```
+
+### `to_text()` — Markdown stripped
+
+Inline markers (`**bold**`, `*em*`, `` `code` ``, `[link](url)`,
+`![alt](url)`) are reduced to their visible text. Bullets become
+`- ` lines, ordered items become `1. `, nested children indent four
+spaces, and fenced code is kept verbatim:
+
+```python
+print(s.to_text())
+# Some content here.
+#
+# - Lightweight — small footprint.
+# - Flexible — extensible by design.
+# - Tested — full coverage.
+```
+
+### `to_html()` — render to HTML, optionally filter with XPath
+
+```python
+s.to_html()
+# <p>Some content here.</p>
+# <ul>
+# <li><strong>Lightweight</strong> — small footprint.</li>
+# <li><em>Flexible</em> — extensible by design.</li>
+# <li><code>Tested</code> — full coverage.</li>
+# </ul>
+
+s.to_html(xpath=".//ul/li")
+# ['<li><strong>Lightweight</strong> — small footprint.</li>',
+#  '<li><em>Flexible</em> — extensible by design.</li>',
+#  '<li><code>Tested</code> — full coverage.</li>']
+
+s.to_html(xpath=".//strong")
+# ['<strong>Lightweight</strong>']
+```
+
+#### Getting just the text value
+
+When you want the *data* inside the matched elements rather than the
+markup, you have two options:
+
+**1. `as_text=True`** — flatten each match to its text content, including
+text nested inside inline tags (`<strong>`, `<em>`, `<code>`, …):
+
+```python
+s.to_html(xpath=".//ul/li", as_text=True)
+# ['Lightweight — small footprint.',
+#  'Flexible — extensible by design.',
+#  'Tested — full coverage.']
+
+s.to_html(xpath=".//ul/li[1]", as_text=True)
+# ['Lightweight — small footprint.']
+```
+
+**2. `/text()` in the XPath itself** — works without the `as_text` flag,
+but only collects *direct* text nodes. Text wrapped in inline tags is
+skipped:
+
+```python
+s.to_html(xpath=".//ul/li/text()")
+# [' — small footprint.',
+#  ' — extensible by design.',
+#  ' — full coverage.']
+# Note: 'Lightweight' / 'Flexible' / 'Tested' are missing — they sit
+# inside <strong>/<em>/<code>, which /text() doesn't enter.
+```
+
+Use `as_text=True` when items contain inline formatting; use `/text()`
+when you specifically want only the loose text and not the wrapped
+content.
+
+XPath uses `lxml` and is opt-in via the `[xpath]` extra:
+
+```bash
+pip install markdown-extractor[xpath]
+```
+
+Without `lxml`, plain `to_html()` still works — only `to_html(xpath=...)`
+raises `ModuleNotFoundError` with the install hint.
+
+---
+
+## Robust extraction
+
+The header parser walks the document with full block-context awareness,
+so a stray `#` is never mistaken for a header.
+
+| Block | Example | Behaviour |
+|-------|---------|-----------|
+| Fenced code | ```` ``` ```` … ```` ``` ```` (or `~~~`) | Headers inside are ignored |
+| Math block | `$$` … `$$` | Headers inside are ignored |
+| Tables | `\| col \| col \|` rows | Cell contents are ignored |
+| YAML front matter | `---` at line 1, closes on `---`/`...` | Whole block is ignored |
+
+```markdown
+---
+title: My Doc
+# not a real header
+---
+
+# Real Header
+
+```python
+# also not a header
+```
+
+$$
+# definitely not a header
+$$
+```
+
+```python
+MDExtractor(md).list()  # ['Real Header']
+```
+
+ATX headers (`#` … `######`) and Setext underlines (`===` / `---`) are
+both recognised. Skip-level jumps (h1 → h3 → h2) are handled gracefully.
+Any leading whitespace is allowed before a header.
+
+---
+
+## Slices for any granularity
+
+Each `Section` exposes three text views:
+
+| Property | Includes header line? | Includes child sections? |
+|----------|-----------------------|--------------------------|
+| `content` | yes | yes |
+| `body` | no | yes |
+| `text` | no | no — own prose only |
+
+---
+
+## API reference
+
+### `MDExtractor`
+
+| Member | Description |
+|--------|-------------|
+| `MDExtractor(markdown)` | Parse a string. |
+| `MDExtractor.from_file(path, encoding="utf-8")` | Read & parse a file. |
+| `e[""]` / `e.root` | Synthetic root section (whole document). |
+| `e["Title"]` / `e[i]` | Top-level child by title or index. |
+| `"Title" in e` | Membership test. |
+| `iter(e)` / `len(e)` | Iterate top-level children / count them. |
+| `.list()` | Top-level header titles. |
+| `.get_section(*path)` | Strict multi-step descent (raises). |
+| `.get(*path)` | Soft multi-step descent (null sentinel on miss). |
+| `.find(title)` | All sections (any depth) with that title. |
+| `.walk()` / `.headers()` | Depth-first iterator / list of every header. |
+| `.tree()` | ASCII tree of the document's header structure. |
+| `.to_list()` | Body flattened to strings (proxies to root). |
+| `.to_dict()` / `.to_json(**kw)` | Serialise the tree (with body blocks). |
+| `.to_text()` | Body rendered as plain text. |
+| `.to_html(xpath=None, as_text=False)` | Body rendered as HTML, optionally XPath-filtered (`as_text=True` returns text values). |
+| `.block(*indices)` | Soft index into root's body block tree (null Block on miss). |
+| `.content` | Original Markdown source. |
+
+### `Section`
+
+| Member | Description |
+|--------|-------------|
+| `.title` / `.level` | Header text and depth (1–6, or 0 for root). |
+| `.parent` / `.children` | Tree links. |
+| `.path` | Title chain from top-level ancestor down to this node. |
+| `.content` / `.body` / `.text` | Raw text views (see table above). |
+| `.blocks` | Lazy-parsed body block tree. |
+| `section["Title"]` / `section[i]` | Child by title or index (strict). |
+| `section.get(*path)` | Soft multi-step descent (null sentinel on miss). |
+| `section.get_section(*path)` | Strict multi-step descent. |
+| `"Title" in section` | Membership test. |
+| `iter(section)` / `len(section)` | Iterate / count direct children. |
+| `bool(section)` | `False` only for the null sentinel returned by `get()`. |
+| `.list()` | Direct child titles. |
+| `.find(title)` | Recursive search. |
+| `.walk()` | Depth-first iterator over self + descendants. |
+| `.to_list()` | Body flattened to one string per top-level block / item. |
+| `.to_dict()` | Nested dict — `blocks` (body) and `children` (header subsections). |
+| `.to_json(**kw)` | `json.dumps` of `to_dict()`. |
+| `.to_text()` | Body rendered as plain text (Markdown markers stripped). |
+| `.to_html(xpath=None, as_text=False)` | Body rendered as HTML, optionally XPath-filtered (`as_text=True` returns text values). |
+| `.block(*indices)` | Soft index walk into the body block tree (null Block on miss). |
+| `.tree()` | ASCII tree of this subsection. |
+| `str(section)` | Same as `.content`. |
+
+### `Block`
+
+A node in the body block tree.
+
+| Member | Description |
+|--------|-------------|
+| `.kind` | One of `paragraph`, `list`, `ordered_list`, `list_item`, `code`, `blockquote`. |
+| `.text` | The block's own text — raw, with inline Markdown markers preserved. |
+| `.text_plain` | `.text` with inline markers stripped (`**bold**` → `bold`, `[t](u)` → `t`, …). |
+| `.children` | Nested blocks (list items, sub-lists, indented paragraphs). |
+| `.info` | Code-fence language, e.g. `"python"`. |
+| `.get(*indices)` | Soft index walk into `.children` (null Block on miss). Chainable. |
+| `bool(block)` | `False` only for the null sentinel returned by `get()` / `Section.block()`. |
+| `.walk()` | Yield this block and every descendant. |
+| `.to_dict()` | JSON-friendly nested dict. |
+
+---
+
+## Development
+
+```bash
+pip install -e .[dev]
+pytest
+```
+
+---
+
+## License
+
+See [LICENSE](LICENSE).

markdown_extractor-0.1.0.dist-info/RECORD

@@ -0,0 +1,13 @@
+markdown_extractor/__init__.py,sha256=vjSYfc9p3GiUxtuw8ythtqNIExt9gcBgQJn7Lo-pWVQ,500
+markdown_extractor/blocks.py,sha256=S4r2FWZpZp6Z-Hn3Ijn8tD7HRXcOAY_5A7r4-DhyLGo,12026
+markdown_extractor/extractor.py,sha256=PPQHqNOr_QxMkuf52tZp1DKUhxcQjNy3yS9OV8tDpK4,6572
+markdown_extractor/html_renderer.py,sha256=o6-uqQjz5ej0LNzODP8j7L-oPQOEKtTAHFsYpTGtcuk,5673
+markdown_extractor/parser.py,sha256=1m_E5u3-LKisZDtnatx1SJGtZtn0PA5zoZUgGsk1eWw,5189
+markdown_extractor/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+markdown_extractor/section.py,sha256=7a_wzejyqIhnJUhGAa_xGF3Afkeerd9zpt7lHTIiXT0,11598
+markdown_extractor/text_renderer.py,sha256=tlWqRv7S9DTQ9fwo87uCV7QRSN1a-hWB04Njy4o1C4A,3083
+markdown_extractor-0.1.0.dist-info/licenses/LICENSE,sha256=UOZ1F5fFDe3XXvG4oNnkL1-Ecun7zpHzRxjp-XsMeAo,11324
+markdown_extractor-0.1.0.dist-info/METADATA,sha256=bpxy5J1GBrHYdSOfan5MzZYgT2rAeApb4rH8b7qfhKQ,28437
+markdown_extractor-0.1.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+markdown_extractor-0.1.0.dist-info/top_level.txt,sha256=MpTrjC_HWmXaP_qEGNGmtodica8PkFIvqeQ1M3Cae-o,19
+markdown_extractor-0.1.0.dist-info/RECORD,,