feat: updated readme to new dependencies and added marxist.org examples

.gitignore

@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

README.md

@@ -1,3 +1,30 @@
 # mlwerke2pdf
 
-Python module to convert texts on http://www.mlwerke.de into pdfs
+Python module to convert texts on http://www.mlwerke.de or https://www.marxists.org into Portable Document Format files
+
+mlwerke2pdf fetches the linked subsites from the given table of contents and concats them to a single pdf
+
+at this point links and linked images in the pdf are not functional as they point to the mlwerke html structure
+converting them to pdf internal links would be possible but rather complex
+
+
+# dependencies
+uses python modules requests, BeautifulSoup4, urllib and weasyprint
+
+# Usage as commandline util
+python mlwerke2pdf_shutil.py -u URL -o PDF_OUTPUT_PATH [--dry True optional for not writing any files]
+
+use the base / table of contents of a text like https://www.marxists.org/deutsch/archiv/marx-engels/1848/manifest/index.htm as URL
+
+# Usage as Python module
+
+## create MLWerke Object:
+mlwerk = mlwerke2pdf.MLWerk(URL)
+
+use the base / table of contents of a text like https://www.marxists.org/deutsch/archiv/marx-engels/1848/manifest/index.htm as URL
+
+## generate a pdf
+mlwerk.text2pdf(PDF_OUTPUT_PATH)
+
+## or cominded into one line
+mlwerke2pdf.MLWerk(URL).text2pdf(PDF_OUTPUT_PATH)

mlwerke2pdf.py

@@ -0,0 +1,54 @@
+import requests
+from bs4 import BeautifulSoup
+import urllib.parse
+from weasyprint import HTML
+
+class MLWerk:
+    class SubSite:
+        def __init__(self, url):
+            self.url = url
+            self.getsoup()
+
+        def getsoup(self):
+            r = requests.get(self.url)
+            r.encoding = 'UTF-8'
+            self.soup = BeautifulSoup(r.text, 'html.parser')
+        
+    def __init__(self, url):
+        self.url = url
+        self.baseurl = url[:url.rfind('/')] + '/'
+        self.subsites = []
+        self.getsoup()
+    
+    def getsoup(self):
+        r = requests.get(self.url)
+        r.encoding = 'UTF-8'
+        self.soup = BeautifulSoup(r.text, 'html.parser')
+
+    def getsubsites(self, limit = None):
+        i = 0
+        for link in self.soup.find_all('a'):
+            if limit != None and i > limit:
+                break
+            link = link.get('href')
+            if not link == None and not ("#" in link or "/" in link):
+                self.subsites.append(self.SubSite(urllib.parse.urljoin(self.baseurl, link)))
+                i += 1
+    
+    def concatsubsites(self):
+        for subsite in self.subsites:
+            for tag in subsite.soup.body:
+                if (tag != "\n" and tag.name != "a"):
+                    self.soup.body.append(tag)
+
+    def genpdf(self, path):
+        HTML(string=str(self.soup)).write_pdf(path)
+
+    def text2pdf(self, path, dry=False):
+        print("gettings subsites")
+        self.getsubsites()
+        print("concatting subsites")
+        self.concatsubsites()
+        if not dry:
+            print("generating pdf")
+            self.genpdf(path)

mlwerke2pdf_shutil.py

@@ -0,0 +1,14 @@
+import mlwerke2pdf
+import argparse
+
+parser = argparse.ArgumentParser(
+                    prog='MLWerke2PDF',
+                    description='convert texts on http://www.mlwerke.de into Portable Document Format files',
+                    epilog='published under GPL-3 at https://git.roteserver.de/humorhenker/mlwerke2pdf')
+parser.add_argument('-u', '--url', dest='url', help='base / table of contents of a text like http://www.mlwerke.de/me/me04/me04_459.htm', required=True) 
+parser.add_argument('-o', '--pdfpath', dest='pdfpath', help='path for the output pdf', required=True)
+parser.add_argument('--dry', dest='dryrun', default=False, help="dont store any files just dry fetch")
+
+args = parser.parse_args()
+
+mlwerke2pdf.MLWerk(args.url).text2pdf(args.pdfpath, args.dryrun)