Rewrtie using python libraries, use tabs
Signed-off-by: Juraj Oravec <sgd.orava@gmail.com>
This commit is contained in:
parent
0cb72ef82d
commit
c09655294a
|
|
@ -1,12 +1,13 @@
|
||||||
* NovelDownloader
|
* NovelDownloader
|
||||||
Script to download each chapter of the webnovel, merge them together and convert to epub
|
Script to download each chapter of the webnovel and save all as epub.
|
||||||
|
|
||||||
* Dependencies
|
* Dependencies
|
||||||
- ebook-convert (Calibre)
|
- python-beautifulsoup4
|
||||||
|
- python-ebooklib
|
||||||
- python-newspaper3k
|
- python-newspaper3k
|
||||||
|
|
||||||
* Usage
|
* Usage
|
||||||
Set variables name, mainUrl, chapters and fromZero at the beginning of the python file and run the script
|
Set variables name, mainUrl, numberOfChapters and fromZero at the beginning of the python file and run the script.
|
||||||
|
|
||||||
* Author`s comment
|
* Author`s comment
|
||||||
Slowly getting rid of external commands.
|
Basic function is done, requires refactoring.
|
||||||
|
|
|
||||||
|
|
@ -6,18 +6,18 @@ together to create one ebook.
|
||||||
|
|
||||||
import errno
|
import errno
|
||||||
import os
|
import os
|
||||||
import shutil
|
import re
|
||||||
import subprocess
|
|
||||||
import sys
|
|
||||||
from newspaper import Article
|
|
||||||
|
|
||||||
|
from bs4 import BeautifulSoup
|
||||||
|
from ebooklib import epub
|
||||||
|
from newspaper import Article
|
||||||
|
|
||||||
# Book name
|
# Book name
|
||||||
name = "Name"
|
name = "Name"
|
||||||
# Base url, this is used as url = mainUrl + <number of chapter>
|
# Base url, this is used as url = mainUrl + <number of chapter>
|
||||||
mainUrl = "http://example.com/chapter-"
|
mainUrl = "http://example.com/chapter-"
|
||||||
# Number of all chapter
|
# Number of all chapter
|
||||||
chapters = 1
|
numberOfChapters = 1
|
||||||
# Start from 0 or 1 ?
|
# Start from 0 or 1 ?
|
||||||
fromZero = False
|
fromZero = False
|
||||||
|
|
||||||
|
|
@ -25,67 +25,128 @@ fromZero = False
|
||||||
# numerical representation of start for script
|
# numerical representation of start for script
|
||||||
start = 0 if fromZero else 1
|
start = 0 if fromZero else 1
|
||||||
|
|
||||||
|
re_paragraph = re.compile(r"(.+?\n\n|.+?$)", re.MULTILINE)
|
||||||
|
|
||||||
def runInShell(command):
|
chapters = []
|
||||||
"""Run giver string in shell"""
|
|
||||||
process = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE)
|
|
||||||
process.wait()
|
|
||||||
process.communicate()
|
|
||||||
|
|
||||||
|
|
||||||
def download(mainUrl, name, number):
|
def download(number):
|
||||||
"""Download webpage, extract main article, save result"""
|
"""Download webpage, extract main article, save result"""
|
||||||
fileName = os.path.join('chapters', '%s-%d.txt' % (name, number))
|
url = "%s%d" % (mainUrl, number)
|
||||||
url = "%s%d" % (mainUrl, number)
|
|
||||||
|
|
||||||
article = Article(url)
|
article = Article(url)
|
||||||
article.download()
|
article.download()
|
||||||
article.parse()
|
article.parse()
|
||||||
|
|
||||||
# save file
|
chapterText = "%s - %d" % (name, number)
|
||||||
try:
|
header = False
|
||||||
file = open(fileName, "w")
|
|
||||||
file.write(article.text)
|
for match in re_paragraph.finditer(article.text):
|
||||||
file.close()
|
paragraph = match.group()
|
||||||
except OSError as err:
|
paragraph = paragraph.strip()
|
||||||
print("OS error: {0}".format(err))
|
|
||||||
except:
|
if paragraph != "Previous ChapterNext Chapter":
|
||||||
print("Unexpected error:", sys.exc_info()[0])
|
if not header:
|
||||||
raise
|
chapterText += "<h2>%s</h2>" % (paragraph)
|
||||||
|
header = True
|
||||||
|
else:
|
||||||
|
chapterText += "<p>%s</p>\n" % (paragraph)
|
||||||
|
|
||||||
|
chapterHtml = BeautifulSoup(
|
||||||
|
"""<html>
|
||||||
|
<head>
|
||||||
|
<title>...</title>
|
||||||
|
<link rel="stylesheet" type="text/css" href="style/main.css" />
|
||||||
|
</head>
|
||||||
|
<body></body>
|
||||||
|
</html>""",
|
||||||
|
'lxml'
|
||||||
|
)
|
||||||
|
chapterHtml.head.title.string = article.title
|
||||||
|
chapterHtml.body.append(chapterText)
|
||||||
|
|
||||||
|
return str(chapterText)
|
||||||
|
|
||||||
|
|
||||||
|
def packageEbook():
|
||||||
|
ebook = epub.EpubBook()
|
||||||
|
ebook.set_identifier("ebook-%s" % name)
|
||||||
|
ebook.set_title(name)
|
||||||
|
ebook.set_language('en')
|
||||||
|
doc_style = epub.EpubItem(
|
||||||
|
uid="doc_style",
|
||||||
|
file_name="style/main.css",
|
||||||
|
media_type="text/css",
|
||||||
|
content=open("template/style.css").read()
|
||||||
|
)
|
||||||
|
ebook.add_item(doc_style)
|
||||||
|
|
||||||
|
intro_ch = epub.EpubHtml(title="Introduction", file_name='intro.xhtml')
|
||||||
|
intro_ch.add_item(doc_style)
|
||||||
|
intro_ch.content = """
|
||||||
|
<html>
|
||||||
|
<head>
|
||||||
|
<title>Introduction</title>
|
||||||
|
<link rel="stylesheet" href="style/main.css" type="text/css" />
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
<h1>%s</h1>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
|
""" % (name)
|
||||||
|
ebook.add_item(intro_ch)
|
||||||
|
|
||||||
|
ebookChapters = []
|
||||||
|
|
||||||
|
i = start
|
||||||
|
for chapter_data in chapters:
|
||||||
|
chapter = epub.EpubHtml(
|
||||||
|
title="%s - %d" % (name, i),
|
||||||
|
file_name='%s-%d.xhtml' % (name, i)
|
||||||
|
)
|
||||||
|
chapter.add_item(doc_style)
|
||||||
|
chapter.content = chapter_data
|
||||||
|
ebook.add_item(chapter)
|
||||||
|
ebookChapters.append(chapter)
|
||||||
|
|
||||||
|
i += 1
|
||||||
|
|
||||||
|
# Set the TOC
|
||||||
|
ebook.toc = (
|
||||||
|
epub.Link('intro.xhtml', 'Introduction', 'intro'),
|
||||||
|
(epub.Section('Chapters'), ebookChapters)
|
||||||
|
)
|
||||||
|
# add navigation files
|
||||||
|
ebook.add_item(epub.EpubNcx())
|
||||||
|
ebook.add_item(epub.EpubNav())
|
||||||
|
|
||||||
|
# Create spine
|
||||||
|
nav_page = epub.EpubNav(uid='book_toc', file_name='toc.xhtml')
|
||||||
|
nav_page.add_item(doc_style)
|
||||||
|
ebook.add_item(nav_page)
|
||||||
|
ebook.spine = [intro_ch, nav_page] + ebookChapters
|
||||||
|
|
||||||
|
filename = '%s.epub' % (name)
|
||||||
|
print("Saving to '%s'" % filename)
|
||||||
|
if os.path.exists(filename):
|
||||||
|
os.remove(filename)
|
||||||
|
epub.write_epub(filename, ebook, {})
|
||||||
|
|
||||||
|
|
||||||
def main():
|
def main():
|
||||||
"""Start main downloader and converter"""
|
"""Start main downloader and converter"""
|
||||||
try:
|
|
||||||
os.makedirs("chapters")
|
|
||||||
except OSError as e:
|
|
||||||
if e.errno != errno.EEXIST:
|
|
||||||
raise
|
|
||||||
|
|
||||||
# Download all chapters one by one
|
# Download all chapters one by one
|
||||||
print("Downloading...")
|
print("Downloading...")
|
||||||
for i in range(start, chapters + 1, 1):
|
for i in range(start, numberOfChapters + 1, 1):
|
||||||
print("Downloading: ", name, i)
|
print("Downloading: ", name, i)
|
||||||
download(mainUrl, name, i)
|
chapters.append(download(i))
|
||||||
|
|
||||||
# merge all chapter to one file
|
packageEbook()
|
||||||
print("Merging...")
|
|
||||||
command = 'cat "chapters/%s-"{%d..%d}.txt > "%s.txt"' % (name, start, chapters, name)
|
|
||||||
runInShell(command)
|
|
||||||
|
|
||||||
# convert to epub
|
print("Done")
|
||||||
print("Converting...")
|
|
||||||
command = 'ebook-convert "%s.txt" "%s.epub"' % (name, name)
|
|
||||||
runInShell(command)
|
|
||||||
|
|
||||||
# remove download directory
|
|
||||||
print("Removing temporary data...")
|
|
||||||
shutil.rmtree('chapters')
|
|
||||||
os.remove("%s.txt" % (name))
|
|
||||||
|
|
||||||
print("Done")
|
|
||||||
|
|
||||||
|
|
||||||
# if yused standalone start the script
|
# if yused standalone start the script
|
||||||
if __name__ == '__main__':
|
if __name__ == '__main__':
|
||||||
main()
|
main()
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue
Block a user