chore: version bump

`wget --timestamping` (alternatively `-N`) is now used to skip already
existing files

.gitignore

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

README.md

@@ -2,8 +2,9 @@
 web to epub converter for https://projekt-gutenberg.org.
 Requires:
 - [pandoc](https://pandoc.org/)
-- wget
+- [wget](https://www.gnu.org/software/wget/)
-- python
+- [fzf](https://github.com/junegunn/fzf) (only for interactive mode)
+- python (duh)
 ## Usage
 Invoke the script using the url of any page of the book you would like to download:
 ``` 

pyproject.toml

@@ -1,11 +1,12 @@
 [project]
 name = "epub2go"
-version = "1.0"
+version = "1.2"
 description = "EPUB converter using wget, pandoc and python glue"
 readme = "README.md"
 requires-python = ">=3.12"
 dependencies = [
     "beautifulsoup4==4.12.3",
+    "pyfzf>=0.3.1", # hasnt been updated for some time
     "requests==2.32.3",
     "tqdm>=4.67.1",
     "urllib3==2.2.2",

src/epub2go/convert.py

@@ -1,17 +1,24 @@
 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 os, sys
 import importlib.resources as pkg_resources
-from pathlib import Path
+
+
+allbooks_url ='https://www.projekt-gutenberg.org/info/texte/allworka.html'
+root_url = '{url.scheme}://{url.netloc}'.format(url = urlparse(allbooks_url))
+
 class GBConvert():
     #TODO fix toc / headings
     
     def __init__(self,
         url:str,
+        standalone = False,
         ):
         # NOTE move non-code files to data folder
         self.style_path_drama = pkg_resources.files('epub2go').joinpath("drama.css")
@@ -19,6 +26,7 @@ class GBConvert():
         self.root = os.path.dirname(url)
         self.url = urlparse(self.root)
         self.output = self.url.netloc + self.url.path
+        self.standalone = standalone
         
     def get_meta(self):
         response = requests.get(self.root)
@@ -31,9 +39,9 @@ class GBConvert():
     def save_page(self, 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 \
-                    --execute \
                     --tries=5 \
                     --quiet \
                     {url}'''
@@ -67,7 +75,7 @@ class GBConvert():
 
         map(lambda x: self.save_page(os.path.join(self.root, x['href'])), self.toc)
         self.chapters = []
-        for item in tqdm(self.toc):
+        for item in (tqdm(self.toc) if self.standalone else self.toc):
             item_title= item.get_text()
             item_url = os.path.join(self.root, item['href'])
             self.save_page(url=item_url)
@@ -78,12 +86,60 @@ class GBConvert():
         
         self.create_epub(f'{self.title} - {self.author}.epub')
         
-    
+def get_all_books() -> list:
+    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 = {'author': book_author, 'title': book_title, 'url': book_url}
+                books.append(book)
+    return books
+
+def get_all_book_tags ()-> ResultSet:
+    response = requests.get(allbooks_url)
+    response.raise_for_status()
+    soup = BeautifulSoup(response.content, 'html.parser', from_encoding='utf-8')
+    books = soup.find('dl').find_all('a')
+    return books
     
 def main():
-    g = GBConvert(sys.argv[1])
+    sys.argv.pop(0)
-    g.run()
+    # non-interactive mode
-
+    if len(sys.argv) > 0 :
+        books = sys.argv
+    # interactive mode using fzf
+    else:
+        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]
 
+    if len(books)==1:
+        GBConvert(books[0], standalone=True).run()
+    else:
+        for book in tqdm(books):
+                GBConvert(book).run()
 if __name__ == "__main__":
     main()

src/epub2go/crawl.py

@@ -0,0 +1,21 @@
+import requests
+from tqdm import tqdm
+
+import os
+from urllib.parse import urljoin
+
+from convert import GBConvert, get_all_book_tags, allbooks_url
+
+def main():
+    books = get_all_book_tags()
+    # NOTE consider making this a map()
+    for book in tqdm(books):
+        book_title = book.get_text()
+        book_url_relative = book.get('href')
+        if book_url_relative is not None:
+            book_url = urljoin(allbooks_url, book_url_relative)
+            GBConvert(book_url).run()
+
+
+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()

src/epub2go/web.py

@@ -0,0 +1,38 @@
+# run using `django-admin runserver --pythonpath=. --settings=web`
+from django.urls import path
+from django.http import HttpResponse, HttpRequest
+from django.shortcuts import redirect, render 
+import requests
+
+from convert import GBConvert, allbooks_url
+import json
+DEBUG = True
+ROOT_URLCONF = __name__
+SECRET_KEY='1'
+TEMPLATES = [
+        {
+            'BACKEND': 'django.template.backends.django.DjangoTemplates',
+            'DIRS': [
+                'templates/'
+            ],
+        },
+    ]
+
+def root(request: HttpRequest):
+    title = 'epub2go'
+    targetParam = request.GET.get('t', None)
+    if targetParam is not None:
+        getEpub(targetParam)
+    return render(request, 'index.html', locals())
+
+urlpatterns = [
+    path('', root, name='root'),
+]
+
+def getEpub(param):
+    # TODO validate / sanitize input
+    # TODO check for existing file and age
+    # TODO download
+    # TODO redirect to loading page
+    # TODO redirect to download page
+    raise NotImplementedError

uv.lock

@@ -72,6 +72,7 @@ version = "1.0"
 source = { editable = "." }
 dependencies = [
     { name = "beautifulsoup4" },
+    { name = "pyfzf" },
     { name = "requests" },
     { name = "tqdm" },
     { name = "urllib3" },
@@ -80,6 +81,7 @@ dependencies = [
 [package.metadata]
 requires-dist = [
     { name = "beautifulsoup4", specifier = "==4.12.3" },
+    { 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 +96,15 @@ 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"