feat: allow getting directory without download

errors from wget and pandoc are thrown up

.gitignore

@@ -418,3 +418,4 @@ wheels/
 *.css
 *.js
 *.txt
+*.json

README.md

@@ -1,17 +1,39 @@
 # epub2go.py
-web to epub converter for https://projekt-gutenberg.org.
+Web to ePUB Converter for [projekt-gutenberg.org](https://projekt-gutenberg.org)  developed in conjunction with a [web interface](https://github.com/eneller/epub2go-web).
+
+## Installation
 Requires:
 - [pandoc](https://pandoc.org/)
-- wget
-- python
-## Usage
-Invoke the script using the url of any page of the book you would like to download:
-``` 
-epub2go https://www.projekt-gutenberg.org/ibsen/solness/
+- [wget](https://www.gnu.org/software/wget/)
+- [fzf](https://github.com/junegunn/fzf) (optional, only for interactive mode)
+- [python](https://www.python.org/) (duh)
+
+Assuming you have a recent version of python installed, run
+
+```
+pip install git+https://github.com/eneller/epub2go.py
+```
+This will provide the `epub2go` command.
+
+## Usage
+```
+Usage: epub2go [OPTIONS] [ARGS]...
+
+  Download ePUBs from https://www.projekt-gutenberg.org/
+
+  Provide either 0 arguments to enter interactive mode or an arbitrary number
+  of URLs to download from
+
+Options:
+  -d, --debug      Set the log level to DEBUG
+  -s, --silent     Disable the progress bar
+  -p, --path TEXT  The path to which files are saved
+  --no-clean       Do not parse html files with blocklist
+  --help           Show this message and exit.
+```
+
+Examples:
+```bash
+epub2go https://www.projekt-gutenberg.org/ibsen/solness/
+epub2go # will enter interactive mode
 ```
-## Installation
-   Assuming you have a recent version of python installed, run
-   ```
-   pip install git+https://github.com/eneller/epub2go.py
-   ```
-   This will provide the 'epub2go' command.

pyproject.toml

@@ -1,11 +1,13 @@
 [project]
 name = "epub2go"
-version = "1.0"
+version = "2.2"
 description = "EPUB converter using wget, pandoc and python glue"
 readme = "README.md"
 requires-python = ">=3.12"
 dependencies = [
     "beautifulsoup4==4.12.3",
+    "click>=8.1.8",
+    "pyfzf>=0.3.1", # hasnt been updated for some time
     "requests==2.32.3",
     "tqdm>=4.67.1",
     "urllib3==2.2.2",
@@ -20,4 +22,4 @@ include-package-data = true
 requires = ["setuptools>=64", "setuptools_scm>=8"]
 
 [tool.setuptools_scm]
-# can be empty if no extra settings are needed, presence enables setuptools-scm
+# can be empty if no extra settings are needed, presence enables setuptools-scm

src/epub2go/convert.py

@@ -1,89 +1,200 @@
 import requests
 from bs4 import BeautifulSoup
+from bs4 import ResultSet
 from urllib.parse import urljoin
-from urllib.request import urlopen, urlparse
+from urllib.request import  urlparse
 from tqdm import tqdm
+from pyfzf.pyfzf import FzfPrompt
+import click
 
-import os, sys
+import os, subprocess, shlex, logging
 import importlib.resources as pkg_resources
-from pathlib import Path
+from dataclasses import dataclass
+from typing import List
+
+logger = logging.getLogger(__name__)
+
+allbooks_url ='https://www.projekt-gutenberg.org/info/texte/allworka.html'
+
+@dataclass
+class Book():
+    author: str
+    title: str
+    url: str
 class GBConvert():
-    #TODO fix toc / headings
-    
     def __init__(self,
-        url:str,
+        downloaddir,
         ):
         # NOTE move non-code files to data folder
         self.style_path_drama = pkg_resources.files('epub2go').joinpath("drama.css")
-        self.blocklist = open(pkg_resources.files('epub2go').joinpath('blocklist.txt')).read().splitlines()
-        self.root = os.path.dirname(url)
-        self.url = urlparse(self.root)
-        self.output = self.url.netloc + self.url.path
+        with open(pkg_resources.files('epub2go').joinpath('blocklist.txt')) as blocklist:
+            self.blocklist = blocklist.read().splitlines()
+        self.dir_download = downloaddir
+
+    def getDir(self, url):
+        tocpage = os.path.dirname(url) # ToC website url
+        parsed_url = urlparse(tocpage)
+        # directories created by wget recreating the URL
+        dir_output = os.path.join(self.dir_download, parsed_url.netloc + parsed_url.path )
+        return dir_output
         
-    def get_meta(self):
-        response = requests.get(self.root)
+    def download(self,
+        url:str,
+        author:str = None,
+        title:str = None,
+        showprogress: bool = False,
+        cleanpages: bool = True,
+    ):
+        tocpage = os.path.dirname(url) # ToC website url
+        dir_output = self.getDir()
+        logger.debug('Downloading to %s, expecting files in in %s', self.dir_download, dir_output)
+        author = author
+        title = title
+
+        #parse_meta
+        response = requests.get(tocpage)
         response.raise_for_status()
         soup = BeautifulSoup(response.content, 'html.parser')
-        self.author = soup.find('meta', {'name': 'author'})['content']
-        self.title = soup.find('meta', {'name': 'title'})['content']
-        self.toc = soup.find('ul').find_all('a')
-    
-    def save_page(self, url):
-        # https://superuser.com/questions/970323/using-wget-to-copy-website-with-proper-layout-for-offline-browsing
-        command = f'''wget \
-                    --page-requisites \
-                    --convert-links \
-                    --execute \
-                    --tries=5 \
-                    --quiet \
-                    {url}'''
-        os.system(command)
+        # TODO allow setting these from interactive mode where those parameters are figured out from the list
+        if not author:
+            try:
+                author = soup.find('meta', {'name': 'author'})['content']
+            except:
+                author = "UnknownAuthor"
+        if not title:
+            try:
+                title = soup.find('meta', {'name': 'title'})['content']
+            except:
+                title = "UnknownTitle"
+        chapter_urls = soup.find('ul').find_all('a')
+        logger.debug('Found ToC with %d entries', len(chapter_urls))
 
-    def clean_page(self,file_path):
-        f = open(file_path, 'r').read()
-        soup = BeautifulSoup(f, 'html.parser')
-        for blocker in self.blocklist:
-            for item in soup.select(blocker):
-                item.decompose()
-        open(file_path, 'w').write(str(soup))
+        #run
+        #TODO include images flag
+        # download all files in toc (chapters)
+        chapter_files = []
+        for item in (tqdm(chapter_urls) if showprogress else chapter_urls):
+            item_url = self.parse_toc_entry(tocpage, item)
+            parsed_url = urlparse(item_url)
+            filepath = os.path.join(self.dir_download, parsed_url.netloc + parsed_url.path)
+            if cleanpages: self.parse_page(filepath)
+            chapter_files.append(os.path.basename(item_url))
+        
+        return self.create_epub(author,title,chapter_files,dir_output)
+        
+    def parse_toc_entry(self, tocpage, entry):
+        url = os.path.join(tocpage, entry['href'])
+        self.save_page(url)
+        return url
 
+    # apply blocklist to file
+    def parse_page(self,file_path):
+        #TODO clean up file opening, mmap?
+        count=0
+        with open(file_path, 'r+') as f:
+            soup = BeautifulSoup(f.read(), 'html.parser')
+            for blocker in self.blocklist:
+                for item in soup.select(blocker):
+                    item.decompose()
+                    count+=1
+            f.seek(0)
+            f.truncate()
+            f.write(str(soup))
+        logger.debug('Removed %d tags from page %s during parsing', count, file_path)
 
-    def create_epub(self,  filename='out.epub'):
-        os.chdir(self.output)
+    def create_epub(self, author, title, chapters, dir_output):
+        #TODO --epub-cover-image
+        #TODO toc if it isnt described by <h> tags, e.g. https://www.projekt-gutenberg.org/adlersfe/maskenba/
+        filename = f'{title} - {author}.epub'
+        logger.debug('Creating epub as "%s"',filename)
         command = f'''pandoc -f html -t epub \
                     -o "{filename}" \
                     --reference-location=section \
                     --css="{self.style_path_drama}" \
-                    --metadata title="{self.title}" \
-                    --metadata author="{self.author}" \
+                    --metadata title="{title}" \
+                    --metadata author="{author}" \
                     --epub-title-page=false \
-                    {" ".join(self.chapters)} '''#TODO --epub-cover-image
-        os.system(command)
+                    {" ".join(chapters)} '''
+        subprocess.run(shlex.split(command), cwd=dir_output, check=True)
+        return os.path.abspath(os.path.join(dir_output,filename))
 
-    def run(self):
-        #TODO include images flag
+    def save_page(self, url):
+        logger.debug('Saving page at %s', url)
+        # https://superuser.com/questions/970323/using-wget-to-copy-website-with-proper-layout-for-offline-browsing
+        command = f'''wget \
+                    --timestamping \
+                    --page-requisites \
+                    --convert-links \
+                    --tries=5 \
+                    --quiet \
+                    {url}'''
+        subprocess.run(shlex.split(command), cwd=self.dir_download, check=True)
 
-        self.get_meta()
+# get a list of all books for interactive selection or scraping
+def get_all_books() -> List[Book]:
+    response = requests.get(allbooks_url)
+    response.raise_for_status()
+    soup = BeautifulSoup(response.content, 'html.parser', from_encoding='utf-8')
+    tags = soup.find('dl').findChildren()
+    books = []
+    for tag in tags:
+        # is description tag, i.e. contains author name
+        if tag.name =='dt':
+            # update author
+            # special case when author name and Alphabetical list is in same tag
+            br_tag = tag.find('br')
+            if br_tag:
+                book_author = str(br_tag.next_sibling)
+            # default case, dt only contains author name
+            else:
+                book_author = tag.get_text(strip=True)
+            book_author = ' '.join(book_author.split())
+        # is details tag, contains book url
+        elif tag.name == 'dd':
+            book_tag = tag.a
+            if book_tag:
+                book_href = book_tag.get('href')
+                book_url = urljoin(allbooks_url, book_href)
+                book_title = ' '.join(book_tag.getText().split())
+                book = Book(book_author, book_title, book_url)
+                books.append(book)
+    return books
 
-        map(lambda x: self.save_page(os.path.join(self.root, x['href'])), self.toc)
-        self.chapters = []
-        for item in tqdm(self.toc):
-            item_title= item.get_text()
-            item_url = os.path.join(self.root, item['href'])
-            self.save_page(url=item_url)
-            parsed_url = urlparse(item_url)
-            filepath = parsed_url.netloc + parsed_url.path
-            self.clean_page(filepath)
-            self.chapters.append(item['href'])
-        
-        self.create_epub(f'{self.title} - {self.author}.epub')
-        
-    
-    
-def main():
-    g = GBConvert(sys.argv[1])
-    g.run()
+# run main cli
+@click.command()
+#TODO include images flag
+@click.option('--debug', '-d', is_flag=True, help='Set the log level to DEBUG')
+@click.option('--silent', '-s', is_flag=True, help='Disable the progress bar')
+@click.option('--path','-p',type=str,default='./', help='The path to which files are saved' )
+@click.option('--no-clean',is_flag=True,help='Do not parse html files with blocklist')
+@click.argument('args', nargs=-1)
+def main(args, debug, silent, path, no_clean):
+    '''
+    Download ePUBs from https://www.projekt-gutenberg.org/ \n
+    Provide either 0 arguments to enter interactive mode or an arbitrary number of URLs to download from
+    '''
+    logging.basicConfig(level=logging.ERROR,format='%(asctime)s - %(levelname)s - %(message)s')
+    if(debug): logger.setLevel(logging.DEBUG)
+    # non-interactive mode
+    if len(args) > 0 :
+        books = args
+    # interactive mode using fzf
+    else:
+        logger.debug('Received no CLI arguments, starting interactive mode')
+        delimiter = ';'
+        # create lines for fzf
+        books = [f"{ item.author } - { item.title } {delimiter} { item.url }" for item in get_all_books()]
+        fzf = FzfPrompt()
+        selection = fzf.prompt(choices=books,  fzf_options=r'--exact --with-nth 1 -m -d\;')
+        books = [item.split(';')[1].strip() for item in selection]
 
+    logger.debug('Attempting to download from %d URL(s)', len(books))
+    converter = GBConvert(path)
+    if len(books)==1:
+        converter.download(books[0], showprogress=not silent, cleanpages= not no_clean)
+    else:
+        for book in (tqdm(books) if not silent else books):
+            converter.download(book, cleanpages= not no_clean)
 
 if __name__ == "__main__":
     main()

src/epub2go/crawl.py

@@ -0,0 +1,21 @@
+import requests
+from tqdm import tqdm
+from bs4 import BeautifulSoup
+from bs4 import ResultSet
+
+import os
+from urllib.parse import urljoin
+
+from convert import GBConvert, allbooks_url, get_all_books, Book
+
+def main():
+    books = get_all_books()
+    # NOTE consider making this a map()
+    converter = GBConvert('./')
+    for book in tqdm(books):
+        if book.url is not None:
+            converter.download(book.url)
+
+
+if __name__ == "__main__":
+    main()

src/epub2go/prosa.css

@@ -0,0 +1,636 @@
+/* Modifizierte Prosa Styles von www.projekt-gutenberg.org - Stand: Januar 2020 */
+@page {
+  margin: 5pt;
+}
+body {
+  font-family: serif;
+  /*font-family: arial;margin-right: 10%;margin-left: 10%;margin-top: 0%;margin-bottom: 3%;*/
+}
+/* Inhaltsverzeichnis */
+.toc {
+  display: none;
+}
+/********************* Links *********************/
+a:link {
+  color: #039;
+  text-decoration: none;
+}
+/* Titelseite */
+.title {
+  /*to be set */
+}
+.subtitle {
+  color: darkgray;
+}
+.author {
+  color: gray;
+}
+.authorlist {
+  text-align: left;
+}
+.box {
+  margin-top: 1.5em;
+  margin-left: 15%;
+  margin-right: 15%;
+  margin-bottom: 1.5em;
+  padding-top: 1em;
+  padding-left: 1em;
+  padding-right: 1em;
+  padding-bottom: 1em;
+  border-top: 1px #666 solid;
+  border-right: 1px #666 solid;
+  border-bottom: 1px #666 solid;
+  border-left: 1px #666 solid;
+}
+.dedication {
+  text-indent: 0;
+  text-align: center;
+  font-size: large;
+  margin-top: 2em;
+  margin-bottom: 2em;
+  margin-left: 20%;
+  margin-right: 20%;
+}
+/* Abbildungen */
+img {
+  max-width: 100%;
+}
+img.initial {
+  float: left;
+  margin-top: 0;
+  margin-bottom: 0;
+  margin-right: 0.3em;
+}
+img.left {
+  float: left;
+  margin-top: 0.5em;
+  margin-bottom: 0.5em;
+  margin-right: 0.5em;
+}
+img.right {
+  float: right;
+  margin-top: 0.5em;
+  margin-bottom: 0.5em;
+  margin-left: 0.5em;
+}
+img.deko {
+  margin-bottom: 20px;
+  margin-top: 10px;
+  border: 1px solid #606060;
+  text-align: center;
+}
+.figcaption {
+  text-indent: 0;
+  text-align: center;
+  font-style: italic;
+}
+.figure {
+  text-indent: 0;
+  text-align: center;
+  margin-top: 1em;
+  margin-bottom: 1em;
+}
+/* Textformatierungen */
+.fraktur {
+  font-family: "Frankenstein", Times, serif;
+}
+.smallcaps {
+  font-variant: small-caps;
+}
+.lektorat {
+  color: darkgrey;
+  font-size: small;
+}
+.motto {
+  text-indent: 0;
+  margin-left: 50%;
+  margin-top: 1em;
+  margin-bottom: 1em;
+}
+.note {
+  line-height: 90%;
+  font-size: 90%;
+}
+.recipient {
+  margin-left: -1em;
+  margin-top: 1em;
+  margin-bottom: 1em;
+}
+/* Regie-Anweisung im Schauspiel */
+.regie, .action {
+  font-size: 90%;
+  font-style: italic;
+}
+/*.sender {
+  margin-left: 2em;
+  font-style: italic;
+  font-weight: bold;
+  color: darkblue;
+  margin-left: 2em;
+}*/
+.signatur, .signature {
+  text-align: right;
+  margin-right: 2em;
+}
+/* Sprecher im Schauspiel. geändert. Re. */
+.speaker {
+  color: #333;
+  font-weight: bold;
+}
+/* Sperrsatz (Duden: Satzzeichen außer Punkt und Anführungszeichen werden mit gesperrt, Zahlen werden's nicht), wird von einigen Readern nicht unterstützt */
+.wide, .spaced {
+  letter-spacing: 0.15em;
+}
+/******************** Überschriften ********************/
+h1, h2, h3, h4, h6 {
+  text-align: center;
+}
+h5 {
+  text-align: center;
+  font-size: 90%;
+  color: #808080;
+  font-weight: normal;
+}
+/******************** Fließtext ********************/
+p {
+  margin-top: 0.4em;
+  margin-bottom: 0.4em;
+  text-indent: 0.8em;
+  text-align: justify;
+  widows: 2;
+  orphans: 2;
+}
+p.abstract {
+  font-size: 90%;
+  font-style: italic;
+  margin-left: 3em;
+  margin-right: 3em;
+  text-indent: 0;
+}
+p.center {
+  text-indent: 0;
+  text-align: center;
+}
+p.centerbig {
+  margin-bottom: 0.6em;
+  margin-top: 0.6em;
+  text-indent: 0;
+  text-align: center;
+  font-size: 115%;
+}
+p.centersml {
+  text-indent: 0;
+  text-align: center;
+  font-size: 90%;
+  margin-bottom: 0.3em;
+  margin-top: 0.3em;
+}
+p.dblmarg {
+  text-indent: 0;
+  margin-left: 10%;
+  margin-right: 10%;
+  text-align: justify;
+}
+p.drama {
+  margin-left: 2em;
+  text-indent: -2em;
+  margin-top: 0.5em;
+  margin-bottom: 0.5em;
+}
+p.epigraph {
+  text-indent: 0;
+  text-align: right;
+  margin-right: 5%;
+  font-style: italic;
+}
+p.left {
+  text-indent: 0;
+  text-align: left;
+  text-align: justify;
+}
+p.initial {
+  text-indent: 0;
+}
+p.leftjust {
+  text-indent: 0;
+  text-align: justify;
+}
+/*p.leftmarg {
+  text-indent: 0;
+  text-align: left;
+  margin-left: 2em;
+  text-align: justify;
+}*/
+/********************* Linien im Text *********************/
+hr {
+  text-align: center;
+  color: #999;
+  margin-top: 0.5em;
+  margin-bottom: 0.5em;
+  /*border-top: 1px solid;border-right: 1px solid;border-bottom: 1px solid;border-left: 1px solid;*/
+  border: 1px solid;
+}
+hr.short {
+  color: #666;
+  margin-top: 2em;
+  margin-bottom: 2em;
+  width: 20%;
+  height: 1px;
+  margin-left: 40%;
+}
+hr.star {
+  margin-top: 1em;
+  margin-bottom: 1em;
+  width: 20%;
+  margin-left: 40%;
+}
+/********************* Absatzübergreifende Formatierung ********************/
+div.epigraph {
+  margin-left: 50%;
+  margin-right: 5%;
+  font-style: italic;
+}
+div.impressum {
+  display: none;
+}
+div.motto p {
+  text-align: right;
+  text-indent: 0;
+}
+div.navi {
+  text-align: center;
+}
+div.titlepage {
+  text-align: center;
+}
+/********************* Gedichte *********************/
+div.poem {
+  margin-left: 20%;
+  margin-right: 20%;
+  margin-bottom: 2em;
+}
+div.poem blockquote {
+  margin-left: 3em;
+  margin-right: 3em;
+}
+div.vers {
+  text-indent: 0;
+  text-align: left;
+  margin-left: 2em;
+  margin-top: 1em;
+  margin-bottom: 1em;
+}
+div.vers p {
+  text-indent: 0;
+  margin-top: 0;
+  margin-bottom: 0;
+}
+p.line {
+  text-align: left;
+  text-indent: 0;
+  margin-top: 0;
+  margin-bottom: 0;
+}
+p.poem, p.vers {
+  text-align: left;
+  text-indent: 0;
+  margin-top: 1em;
+  margin-left: 2em;
+  margin-right: 2em;
+  margin-bottom: 1em;
+}
+/********************* Briefe *********************/
+div.letter {
+  text-align: left;
+  margin-left: 1.5em;
+  margin-top: 1em;
+  margin-bottom: 1em;
+}
+p.address {
+  text-align: right;
+  text-indent: 0;
+  font-style: italic;
+}
+p.date {
+  text-align: right;
+  font-style: italic;
+}
+/********************* Tabellen  *********************/
+tbody {
+  /*font-family: arial;*/
+}
+td {
+  /*font-family: arial;*/
+}
+/* Wird für mehrspaltige 0hmldir.xml gebraucht */
+table.dirtoc {
+  margin-top: 0.3em;
+  margin-bottom: 0.3em;
+  text-align: left;
+}
+/* 0.4em Horizontal-Abstand zu Trennlinien, Folgezeilen um 1em eingerückt */
+table.dirtoc td {
+  padding-top: 0;
+  padding-bottom: 0;
+  padding-left: 1.4em;
+  padding-right: 0.4em;
+  text-indent: -1em;
+}
+/* Notwendig, wenn jemand heimlichtückisch <div align="center"> davorsetzt: */
+table.left {
+  margin-left: 0;
+  text-align: left;
+}
+table.motto {
+  margin-left: 30%;
+  margin-right: 0;
+}
+table.right {
+  margin-right: 0;
+}
+table.toc {
+  margin-top: 0.3em;
+}
+table.toc td {
+  padding-top: 0;
+  padding-left: 0.25em;
+  padding-right: 0.25em;
+  padding-bottom: 0;
+  text-align: left;
+}
+table.true, table.real {
+  margin-top: 0.3em;
+  margin-bottom: 0.3em;
+  text-align: left;
+}
+/* Definitionsliste */
+dd {
+  margin-left: 2em;
+}
+dl {
+  margin-left: 1.5em;
+  margin-top: 1em;
+  margin-bottom: 1em;
+}
+dt {
+  font-weight: bold;
+  margin-top: 4pt;
+}
+/* Ungeordnete Liste */
+ul {
+  margin-top: 1em;
+  margin-bottom: 1em;
+}
+/* Löschung und Einfügung */
+del {
+  color: red;
+}
+ins {
+  color: blue;
+}
+/* Zeile mit 3 Sternen: <p class="stars"><sup>*</sup> <sub>*</sub> <sup>*</sup></p> */
+p.stars {
+  text-indent: 0;
+  text-align: center;
+  font-size: 200%;
+  letter-spacing: 0.3em;
+  margin-top: 0.5em;
+  margin-bottom: 0;
+}
+/* Hochstellung ohne Vergößerung des Zeilenabstandes */
+sup {
+  font-size: 70%;
+  vertical-align: text-top;
+}
+sub {
+  font-size: 70%;
+  vertical-align: text-bottom;
+}
+/* Formatierung von Brüchen */
+sup.fract {
+  font-size: 70%;
+  vertical-align: text-top;
+}
+sub.fract {
+  font-size: 70%;
+  vertical-align: text-bottom;
+}
+.mainnav {
+  /*font-family: Arial;*/
+  background-color: #fff;
+  text-align: center;
+  border-top: 1px #d26402 solid;
+  border-bottom: 1px #d26402 solid;
+}
+.autalpha {
+  /*font-family: Arial;*/
+  text-align: center;
+}
+.trenner {
+  font-size: 10pt;
+  font-weight: bold;
+  color: #d26402;
+}
+.right {
+  text-align: right;
+}
+.left {
+  text-align: left;
+}
+/* Zu überprüfende Klassen: sind sie korrekt oder machen sie Sinn für ein EBook? */
+.hidden, .hide {
+  display: none;
+}
+upper {
+  /* .upper ? */
+  text-transform: uppercase;
+}
+p.initial:first-letter {
+  /* funktioniert nicht bei allen Readern */
+  font-size: 150%;
+}
+.online {
+  display: none;
+}
+/* Seitennummern */
+.pageref {
+  /* noch nicht definiert */
+}
+a.pageref {
+  display: none;
+}
+a.pageref:before {
+  content: "[";
+}
+a.pageref:after {
+  content: "]";
+}
+tt {
+  font-family: Courier;
+}
+/* besser 
+
+span.truetype {
+  font-family: monospace;
+}*/
+/********************* Anmerkungen und Fußnoten. geändert. Re. *********************/
+a:visited {
+  color: #039;
+  text-decoration: none;
+}
+a:hover {
+  color: #039;
+  text-decoration: none;
+  background-color: #e0e0e0;
+}
+a:active {
+  color: #039;
+  text-decoration: none;
+}
+span.tooltip {
+  color: #800000;
+}
+span.footnote a:hover {
+  background-color: #2B2E21;
+  color: #fff;
+}
+span.footnote a:link span, span.footnote a:visited span {
+  display: none;
+}
+span.footnote a:hover span.fntext {
+  position: absolute;
+  margin: 20px;
+  background-color: beige;
+  max-width: 400px;
+  padding: 5px 10px 5px 10px;
+  border: 1px solid #C0C0C0;
+  font: normal 12px/14px arial;
+  color: #000;
+  text-align: left;
+  display: block;
+  text-decoration: none;
+  left: 10px;
+}
+span.footnote:before {
+  content: " [Fußnote: ";
+  color: #505050;
+}
+span.footnote:after {
+  content: "] ";
+  color: #505050;
+}
+span.footnote {
+  color: #505050;
+  display: inline;
+  font-size: 90%;
+}
+span.teletype {
+  font-family: monospace;
+}
+/* Alte Klassen */
+.overline {
+  text-decoration: overline;
+}
+.upper {
+  text-transform: uppercase;
+}
+p.end {
+  text-indent: 0;
+  text-align: center;
+}
+p.right {
+  text-indent: 0;
+  text-align: right;
+}
+div.footnote {
+  display: inline;
+}
+table.poem, table.vers {
+  margin-left: auto;
+  margin-right: auto;
+}
+td.left {
+  text-align: left;
+}
+td.right {
+  text-align: right;
+}
+td.center {
+  text-align: center;
+}
+/* mit dem lang-Attribut markierte Tags. geändert. Re. */
+*[lang=""] {
+  color: grey;
+}
+*[lang="fr"] {
+  color: red;
+}
+*[lang="la"] {
+  color: blue;
+}
+*[lang="en"] {
+  color: green;
+}
+*[lang="it"] {
+  color: violet;
+}
+*[lang="el"] {
+  color: brown;
+}
+/* ******************************************************************* */
+/*    Zusätzliche Definitionen ohne Layout für Text-Strukturierung     */
+/* ******************************************************************* */
+div.ballad {
+  /* styles hier einfügen */
+}
+div.chapter {
+  /* styles hier einfügen */
+}
+div.part {
+  /* styles hier einfügen */
+}
+div.preface {
+  /* styles hier einfügen */
+}
+div.section {
+  /* styles hier einfügen */
+}
+div.volume {
+  /* styles hier einfügen */
+}
+h3.date {
+  /* styles hier einfügen */
+}
+h3.subtitle {
+  /* styles hier einfügen */
+}
+h3.translator {
+  /* styles hier einfügen */
+}
+h4.date {
+  /* styles hier einfügen */
+}
+h4.pseudo {
+  /* styles hier einfügen */
+}
+h4.publisher {
+  /* styles hier einfügen */
+}
+h4.subtitle {
+  /* styles hier einfügen */
+}
+h4.translator {
+  /* styles hier einfügen */
+}
+h5.date {
+  /* styles hier einfügen */
+}
+h5.translator {
+  /* styles hier einfügen */
+}
+div.toc {
+  display: none;
+}
+p.toc {
+  display: none;
+}

src/epub2go/test.py

@@ -1,25 +0,0 @@
-import requests
-from bs4 import BeautifulSoup
-
-import os
-
-from convert import GBConvert
-
-def main():
-    allbooks_relative_url ='/info/texte/allworka.html'
-    root_url = 'https://www.projekt-gutenberg.org'
-    allbooks_url = root_url + allbooks_relative_url
-    response = requests.get(allbooks_url)
-    if (response.status_code != 200): raise Exception(f'Couldnt fetch root page {self.root}')
-    soup = BeautifulSoup(response.content, 'html.parser')
-    books = soup.find('dl').find_all('a')
-    for book in books:
-        book_title = book.get_text()
-        book_url_relative = book.get('href')
-        if book_url_relative is not None:
-            book_url = root_url + os.path.dirname(book_url_relative)[5:]
-            gb = GBConvert(book_url)
-
-
-if __name__ == "__main__":
-    main()

test/test_epub.py

@@ -0,0 +1,23 @@
+from tqdm import tqdm
+
+from src.epub2go.convert import GBConvert, get_all_books
+
+import unittest
+
+# run using `python -m unittest test/test_epub.py`
+class TestEpub(unittest.TestCase):
+
+    @classmethod
+    def setUpClass(cls):
+        cls.schiller_raeuber = GBConvert('https://www.projekt-gutenberg.org/schiller/raeuber/')
+        cls.anzengru_allersee = GBConvert('https://www.projekt-gutenberg.org/anzengru/allersee/')
+
+    def test_schiller_raeuber_toc(self):
+        self.assertEqual(len(self.schiller_raeuber.toc), 7)
+
+    def test_anzengru_allersee_toc(self):
+        self.assertEqual(len(self.anzengru_allersee.toc), 1)
+        
+
+if __name__ == '__main__':
+    unittest.main()

uv.lock

@@ -1,4 +1,5 @@
 version = 1
+revision = 1
 requires-python = ">=3.12"
 
 [[package]]
@@ -57,6 +58,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/0e/f6/65ecc6878a89bb1c23a086ea335ad4bf21a588990c3f535a227b9eea9108/charset_normalizer-3.4.1-py3-none-any.whl", hash = "sha256:d98b1668f06378c6dbefec3b92299716b931cd4e6061f3c875a71ced1780ab85", size = 49767 },
 ]
 
+[[package]]
+name = "click"
+version = "8.1.8"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "colorama", marker = "sys_platform == 'win32'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/b9/2e/0090cbf739cee7d23781ad4b89a9894a41538e4fcf4c31dcdd705b78eb8b/click-8.1.8.tar.gz", hash = "sha256:ed53c9d8990d83c2a27deae68e4ee337473f6330c040a31d4225c9574d16096a", size = 226593 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/7e/d4/7ebdbd03970677812aac39c869717059dbb71a4cfc033ca6e5221787892c/click-8.1.8-py3-none-any.whl", hash = "sha256:63c132bbbed01578a06712a2d1f497bb62d9c1c0d329b7903a866228027263b2", size = 98188 },
+]
+
 [[package]]
 name = "colorama"
 version = "0.4.6"
@@ -68,10 +81,12 @@ wheels = [
 
 [[package]]
 name = "epub2go"
-version = "1.0"
+version = "2.2"
 source = { editable = "." }
 dependencies = [
     { name = "beautifulsoup4" },
+    { name = "click" },
+    { name = "pyfzf" },
     { name = "requests" },
     { name = "tqdm" },
     { name = "urllib3" },
@@ -80,6 +95,8 @@ dependencies = [
 [package.metadata]
 requires-dist = [
     { name = "beautifulsoup4", specifier = "==4.12.3" },
+    { name = "click", specifier = ">=8.1.8" },
+    { name = "pyfzf", specifier = ">=0.3.1" },
     { name = "requests", specifier = "==2.32.3" },
     { name = "tqdm", specifier = ">=4.67.1" },
     { name = "urllib3", specifier = "==2.2.2" },
@@ -94,6 +111,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/76/c6/c88e154df9c4e1a2a66ccf0005a88dfb2650c1dffb6f5ce603dfbd452ce3/idna-3.10-py3-none-any.whl", hash = "sha256:946d195a0d259cbba61165e88e65941f16e9b36ea6ddb97f00452bae8b1287d3", size = 70442 },
 ]
 
+[[package]]
+name = "pyfzf"
+version = "0.3.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/d4/4c/c0c658a1e1e9f0e01932990d7947579515fe048d0a515f07458ecd992b8f/pyfzf-0.3.1.tar.gz", hash = "sha256:dd902e34cffeca9c3082f96131593dd20b4b3a9bba5b9dde1b0688e424b46bd2", size = 3652 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/99/35/6a6c7b95390ec58904646a04f54e1b56fd57d7a247588b791c6331697797/pyfzf-0.3.1-py3-none-any.whl", hash = "sha256:736f71563461b75f6f85b55345bdc638fa0dc14c32c857c59e8b1ca1cfa3cf4a", size = 4315 },
+]
+
 [[package]]
 name = "requests"
 version = "2.32.3"