5 Commits
v1.1 ... v1.2

Author SHA1 Message Date
eneller
bde605cc90 chore: version bump 2025-02-25 23:07:55 +01:00
eneller
f9942a75d3 feat: display authors 2025-02-25 20:09:31 +01:00
eneller
90bdf83950 chore: webserver stuff 2025-02-25 15:51:57 +01:00
eneller
55e1472e1d fix: crawl 2025-02-25 14:09:28 +01:00
eneller
4ffe110bc4 fix: redownloading
`wget --timestamping` (alternatively `-N`) is now used to skip already
existing files
2025-02-25 13:24:51 +01:00
6 changed files with 686 additions and 25 deletions

View File

@@ -13,6 +13,6 @@ epub2go https://www.projekt-gutenberg.org/ibsen/solness/
## Installation
Assuming you have a recent version of python installed, run
```
pip install git+https://github.com/eneller/epub2go.py@latest
pip install git+https://github.com/eneller/epub2go.py
```
This will provide the 'epub2go' command.

View File

@@ -1,6 +1,6 @@
[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"

View File

@@ -37,12 +37,11 @@ class GBConvert():
self.toc = soup.find('ul').find_all('a')
def save_page(self, url):
# TODO fix redownloading of shared content
# 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}'''
@@ -88,15 +87,33 @@ class GBConvert():
self.create_epub(f'{self.title} - {self.author}.epub')
def get_all_books() -> list:
books = get_all_book_tags()
d = []
for book in books:
book_href = book.get('href')
if book_href is not None:
book_url = urljoin(allbooks_url, book_href)
book_title = book.getText().translate(str.maketrans('','', '\n\t'))
d.append({'title': book_title, 'url': book_url})
return d
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)
@@ -114,8 +131,7 @@ def main():
else:
delimiter = ';'
# create lines for fzf
# TODO display author
books = [f"{item['title']} {delimiter} {item['url']}" for item in get_all_books()]
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]

View File

@@ -4,17 +4,16 @@ from tqdm import tqdm
import os
from urllib.parse import urljoin
from convert import GBConvert
import utils
from convert import GBConvert, get_all_book_tags, allbooks_url
def main():
books = utils.get_all_book_tags()
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_href)
book_url = urljoin(allbooks_url, book_url_relative)
GBConvert(book_url).run()

636
src/epub2go/prosa.css vendored Normal file
View File

@@ -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;
}

View File

@@ -1,10 +1,10 @@
# run using `django-admin runserver --pythonpath=. --settings=web`
from django.urls import path
from django.http import HttpResponse
from django.http import HttpResponse, HttpRequest
from django.shortcuts import redirect, render
import requests
import utils
from convert import GBConvert, allbooks_url
import json
DEBUG = True
ROOT_URLCONF = __name__
@@ -18,11 +18,21 @@ TEMPLATES = [
},
]
def home(request):
def root(request: HttpRequest):
title = 'epub2go'
items = json.load(open('dict.json', 'r'))
targetParam = request.GET.get('t', None)
if targetParam is not None:
getEpub(targetParam)
return render(request, 'index.html', locals())
urlpatterns = [
path('', home, name='homepage'),
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