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

README.md

@@ -1,12 +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
 
-# Usage
+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 of a text like http://www.mlwerke.de/me/me04/me04_459.htm as 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

@@ -1,7 +1,7 @@
 import requests
 from bs4 import BeautifulSoup
 import urllib.parse
-import pdfkit
+from weasyprint import HTML
 
 class MLWerk:
     class SubSite:
@@ -31,22 +31,24 @@ class MLWerk:
             if limit != None and i > limit:
                 break
             link = link.get('href')
-            if not (link == None and ("#" in link or "/" in link)):
+            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 element in subsite.soup.body:
+            for tag in subsite.soup.body:
-                self.soup.body.append(element)
+                if (tag != "\n" and tag.name != "a"):
+                    self.soup.body.append(tag)
 
     def genpdf(self, path):
-        pdfkit.from_string(str(self.soup), path, options={"enable-local-file-access": ""})
+        HTML(string=str(self.soup)).write_pdf(path)
 
-    def text2pdf(self, path):
+    def text2pdf(self, path, dry=False):
         print("gettings subsites")
-        self.getsubsites
+        self.getsubsites()
         print("concatting subsites")
-        self.concatsubsites
+        self.concatsubsites()
+        if not dry:
             print("generating pdf")
-        self.genpdf(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)