orlydown 0.1.0__py3-none-any.whl

oreilly_downloader.py

@@ -0,0 +1,194 @@
+import argparse
+import json
+import posixpath
+import sys
+import time
+import urllib.error
+import urllib.request
+import zipfile
+from concurrent.futures import ThreadPoolExecutor
+from html.parser import HTMLParser
+from xml.etree import ElementTree as ET
+
+BASE_URL = 'https://learning.oreilly.com'
+
+CONTAINER = """<?xml version="1.0"?>
+<container xmlns="urn:oasis:names:tc:opendocument:xmlns:container" version="1.0">
+    <rootfiles>
+        <rootfile full-path="{}" media-type="application/oebps-package+xml"/>
+    </rootfiles>
+</container>
+"""  # noqa
+
+VOID_ELEMENTS = {
+    'area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input', 'link',
+    'meta', 'source', 'track', 'wbr',
+}
+
+
+class TreeBuilder(HTMLParser):
+    """Parse (possibly sloppy) HTML into an ElementTree."""
+
+    def __init__(self):
+        super().__init__()
+        self.stack = [ET.Element('root')]
+
+    def handle_starttag(self, tag, attrs):
+        el = ET.SubElement(self.stack[-1], tag, {k: v or '' for k, v in attrs})
+        if tag not in VOID_ELEMENTS:
+            self.stack.append(el)
+
+    def handle_endtag(self, tag):
+        # implicitly close any unclosed children, ignore stray end tags
+        if any(el.tag == tag for el in self.stack[1:]):
+            while self.stack.pop().tag != tag:
+                pass
+
+    def handle_data(self, data):
+        parent = self.stack[-1]
+        if len(parent):
+            parent[-1].tail = (parent[-1].tail or '') + data
+        else:
+            parent.text = (parent.text or '') + data
+
+
+def to_xhtml(s, root_path, path, stylesheets):
+    builder = TreeBuilder()
+    builder.feed(s.decode('utf-8'))
+    builder.close()
+    tree = builder.stack[0]
+    base = posixpath.dirname(root_path + path)
+
+    for el in tree.iter():
+        for attr in ['href', 'src']:
+            if (el.get(attr) or '').startswith(root_path):
+                el.set(attr, posixpath.relpath(el.get(attr), base))
+
+    for el in tree.iter('svg'):
+        for attr in ['viewBox', 'preserveAspectRatio']:
+            if attr.lower() in el.attrib:
+                el.set(attr, el.attrib.pop(attr.lower()))
+
+    html = tree.find('html')
+    if html is None:
+        html = ET.Element('html', {
+            'xmlns': 'http://www.w3.org/1999/xhtml',
+            'xmlns:epub': 'http://www.idpf.org/2007/ops',
+        })
+
+        head = ET.SubElement(html, 'head')
+        for href in stylesheets:
+            ET.SubElement(head, 'link', rel='stylesheet', href=posixpath.relpath(root_path + href, base))
+        h1 = tree.find('.//h1')
+        if h1 is not None:
+            title = ET.SubElement(head, 'title')
+            title.text = ''.join(h1.itertext()).strip()
+
+        body = ET.SubElement(html, 'body')
+        body.text = tree.text
+        body.extend(tree)
+
+    return (
+        '<?xml version="1.0" encoding="utf-8"?>\n<!DOCTYPE html>\n'
+        + ET.tostring(html, encoding='unicode')
+    ).encode('utf-8')
+
+
+def make_getter(jwt):
+    headers = {'User-Agent': 'orlydown'}
+    if jwt:
+        headers['Cookie'] = f'orm-jwt={jwt}'
+
+    def get(url):
+        with urllib.request.urlopen(urllib.request.Request(url, headers=headers)) as r:
+            return r.read()
+
+    return get
+
+
+def check_auth(get):
+    try:
+        get(BASE_URL + '/api/v1/user-preferences/')
+        return True
+    except urllib.error.HTTPError:
+        return False
+
+
+def fetch_book(book_id, zfh, get, *, delay=0):
+    root_path = f'/api/v2/epubs/urn:orm:book:{book_id}/files/'
+    html = {}
+
+    def download(result):
+        return f'EPUB/{result["full_path"]}', get(result['url'])
+
+    zfh.writestr('mimetype', b'application/epub+zip', compress_type=zipfile.ZIP_STORED)
+
+    url = BASE_URL + root_path
+    with ThreadPoolExecutor() as pool:
+        while url:
+            print(f'fetching {url}')
+            data = json.loads(get(url))
+
+            for path, content in pool.map(download, data.get('results', [])):
+                if path.endswith(('.html', '.xhtml')):
+                    html[path] = content
+                else:
+                    zfh.writestr(path, content)
+
+            url = data.get('next')
+            if url:
+                time.sleep(delay)
+
+    css = [p.removeprefix('EPUB/') for p in zfh.namelist() if p.endswith('.css')]
+    for path, content in html.items():
+        zfh.writestr(path, to_xhtml(content, root_path, path.removeprefix('EPUB/'), css))
+    opf = next(p for p in zfh.namelist() if p.endswith('.opf'))
+    zfh.writestr('META-INF/container.xml', CONTAINER.format(opf))
+
+
+def main():
+    parser = argparse.ArgumentParser(prog='orlydown')
+    parser.add_argument('book_id', help=(
+        'ID of the book, as found in its URL, '
+        'e.g. 9781491958698 in https://learning.oreilly.com/library/view/…/9781491958698/'
+    ))
+    parser.add_argument('--jwt', metavar='TOKEN', help=(
+        'Value of the orm-jwt cookie from a logged-in browser session. '
+        'Without it, chapters are cut short.'
+    ))
+    parser.add_argument('--require-auth', action='store_true', help=(
+        'Exit with an error instead of downloading truncated chapters '
+        'when no JWT is given or it is not accepted.'
+    ))
+    parser.add_argument('--delay', type=int, default=0, help=(
+        'Seconds to wait between batches of file downloads. '
+        'Workaround for 403 errors caused by rate-limiting.'
+    ))
+    parser.add_argument('--title', action='store_true', help=(
+        'Name the file after the book title instead of its ID.'
+    ))
+    args = parser.parse_args()
+
+    filename = f'{args.book_id}.epub'
+    get = make_getter(args.jwt)
+
+    if args.jwt and check_auth(get):
+        print('Authentication successful.')
+    else:
+        problem = 'Authentication failed.' if args.jwt else 'No JWT provided.'
+        if args.require_auth:
+            sys.exit(problem)
+        print(f'{problem} Continuing without…')
+
+    if args.title:
+        data = json.loads(get(f'{BASE_URL}/api/v2/epubs/urn:orm:book:{args.book_id}/'))
+        filename = data['title'].replace(':', ' -').replace('/', '-') + '.epub'
+
+    with zipfile.ZipFile(filename, 'w') as zfh:
+        fetch_book(args.book_id, zfh, get, delay=args.delay)
+
+    print(f'created {filename}')
+
+
+if __name__ == '__main__':
+    main()

orlydown-0.1.0.dist-info/METADATA

@@ -0,0 +1,156 @@
+Metadata-Version: 2.5
+Name: orlydown
+Version: 0.1.0
+Summary: Download O'Reilly books as epub files you can read in any reader
+Project-URL: Homepage, https://github.com/ashleyconnor/orlydown
+Project-URL: Issues, https://github.com/ashleyconnor/orlydown/issues
+Author: Ashley Connor, Tobias Bengfort
+License-Expression: MIT
+License-File: LICENSE
+Keywords: downloader,ebook,epub,oreilly
+Classifier: Environment :: Console
+Classifier: Intended Audience :: End Users/Desktop
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Utilities
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+
+# orlydown
+
+O'Reilly provides all of their books in epub format, but only through their own
+reader. `orlydown` downloads the individual files and assembles them back into
+a complete epub, so you can read your books in any reader (Apple Books, Calibre,
+KOReader, …), e.g. for accessibility reasons.
+
+Before using it, please read the [O'Reilly Terms of
+Service](https://learning.oreilly.com/terms/).
+
+This is a fork of [xi/oreilly-downloader](https://github.com/xi/oreilly-downloader)
+that fixes epubs which didn't render properly:
+
+-   Stylesheets are linked from every chapter, so books keep their formatting
+    and fonts.
+-   Images and links work in books that keep chapters in a subdirectory
+    (e.g. `Text/`, `Images/`).
+-   Books whose package file isn't called `content.opf` (e.g. Springer titles)
+    open correctly.
+-   SVG covers are scaled to fit the page instead of being cropped.
+-   A `--title` option names the epub after the book instead of its ID.
+-   A `--require-auth` option stops straight away if your token doesn't work.
+-   No dependencies: it only uses the Python standard library.
+
+## Installation
+
+You need Python 3.9 or newer. The easiest way to install `orlydown` is with
+[pipx](https://pipx.pypa.io/), which puts it in its own environment and adds
+the `orlydown` command to your `PATH`:
+
+```
+pipx install orlydown
+```
+
+Upgrade later with `pipx upgrade orlydown`. To run it once without installing
+anything:
+
+```
+pipx run orlydown 9781491958698 --jwt 'XYZ'
+```
+
+With [uv](https://docs.astral.sh/uv/), the equivalents are
+`uv tool install orlydown` and `uvx orlydown …`.
+
+Since there are no dependencies, you can also download
+[`oreilly_downloader.py`](oreilly_downloader.py) and run it directly with
+`python3 oreilly_downloader.py …`.
+
+## Getting your JWT
+
+Without a valid JWT every chapter is cut short. To get one:
+
+1.  Log in to <https://learning.oreilly.com> in your browser.
+2.  Open the developer tools and find the cookies for `learning.oreilly.com`.
+3.  Copy the value of the `orm-jwt` cookie.
+
+If `orlydown` reports `Authentication failed`, log in again and copy a fresh
+cookie.
+
+## Usage
+
+Find the book ID in the book's URL, e.g. `9781491958698` in
+`https://learning.oreilly.com/library/view/test-driven-development-with/9781491958698/`.
+
+```
+$ orlydown 9781491958698 --jwt 'XYZ'
+Authentication successful.
+fetching https://learning.oreilly.com/api/v2/epubs/urn:orm:book:9781491958698/files/
+…
+created 9781491958698.epub
+```
+
+To name the file after the book instead of its ID, add `--title`:
+
+```
+$ orlydown 9781491958698 --jwt 'XYZ' --title
+…
+created Test-Driven Development with Python, 2nd Edition.epub
+```
+
+A `:` in the title becomes ` -` and a `/` becomes `-`, so the name is safe to
+use as a filename.
+
+By default, a missing or rejected token only prints a warning and the download
+carries on with truncated chapters. Add `--require-auth` to stop with an error
+instead, which is useful in scripts:
+
+```
+$ orlydown 9781491958698 --jwt 'expired' --require-auth
+Authentication failed.
+$ echo $?
+1
+```
+
+### Options
+
+| Option           | Description                                                                   |
+| ---------------- | ----------------------------------------------------------------------------- |
+| `--jwt TOKEN`    | Your `orm-jwt` cookie. Without it, chapters are cut short.                    |
+| `--require-auth` | Exit with an error if no JWT is given or it isn't accepted.                   |
+| `--title`        | Name the epub after the book title instead of its ID.                         |
+| `--delay N`      | Wait `N` seconds between batches of downloads. Try `5` if you get 403 errors. |
+
+## Development
+
+The project is managed with [uv](https://docs.astral.sh/uv/):
+
+```
+uv run orlydown --help
+uv build
+```
+
+### Releasing
+
+Pushing a `v*` tag publishes that version to PyPI. The version is the tag name
+without the `v`, so `v1.0.0` publishes `1.0.0`:
+
+```
+git tag v1.0.0
+git push origin v1.0.0
+```
+
+Publishing uses PyPI [trusted
+publishing](https://docs.pypi.org/trusted-publishers/), so no API token is
+stored in the repository. It needs a one-time setup: on PyPI, add a trusted
+publisher for project `orlydown` with owner `ashleyconnor`, repository
+`orlydown`, workflow `publish.yml` and environment `pypi`.
+
+## Similar projects
+
+-   <https://github.com/lorenzodifuccia/safaribooks> (python)
+-   <https://github.com/hurlenko/orly> (rust)
+-   <https://github.com/jenni/obooks> (javascript)
+-   <https://github.com/rahulvramesh/oreilly-books-grabber> (go)
+
+## License
+
+MIT, see [LICENSE](LICENSE).

orlydown-0.1.0.dist-info/RECORD

@@ -0,0 +1,6 @@
+oreilly_downloader.py,sha256=0qiwHLoD2x65057z9G0W_-H3pf-YXG5exLpSkwj9ysQ,6218
+orlydown-0.1.0.dist-info/METADATA,sha256=W2nmesnW-mzS3k_U85_DMcbIXXmQiLJvjdWqZjNmHDk,5243
+orlydown-0.1.0.dist-info/WHEEL,sha256=W3fkpkm7-wf9vBI5Z-7s0eWkeM-spu78I8Neb98DeEg,87
+orlydown-0.1.0.dist-info/entry_points.txt,sha256=_GuRDyDmP7_F9LDhjYSSSV3BcsPPpxkZlgLBxgk4qTw,53
+orlydown-0.1.0.dist-info/licenses/LICENSE,sha256=NMVEu_s-ucif-YlqfJnUAl541NAlkfjgnpbadpdv2ss,1105
+orlydown-0.1.0.dist-info/RECORD,,

orlydown-0.1.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.32.4
+Root-Is-Purelib: true
+Tag: py3-none-any

orlydown-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+orlydown = oreilly_downloader:main

orlydown-0.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,22 @@
+MIT License
+
+Copyright (c) 2025 Tobias Bengfort
+Copyright (c) 2026 Ashley Connor
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.