Created
October 12, 2016 17:05
-
-
Save james-ingold/653175d5fb07bf5ff07d47f235e2bdc4 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding: utf-8 -*- | |
""" | |
Builds epub book out of James Clear's essays: http://jamesclear.com/articles | |
Copyright: Licensed under the GPL-3 (http://www.gnu.org/licenses/gpl-3.0.html) | |
Requires python-epub-library: http://code.google.com/p/python-epub-builder/ | |
""" | |
import re, ez_epub, urllib2, genshi | |
from BeautifulSoup import BeautifulSoup | |
def addSection(link, title): | |
page = urllib2.urlopen(link).read() | |
soup = BeautifulSoup(page) | |
soup.prettify() | |
section = ez_epub.Section() | |
try: | |
section.title = title | |
print section.title | |
entryContent = soup.findAll('div', {'class':'entry-content'})[0] | |
children = entryContent.findChildren() | |
for child in children: | |
print child | |
section.text.append(genshi.core.Markup(child)) | |
except: | |
pass | |
return section | |
book = ez_epub.Book() | |
book.title = "James Clear Essays" | |
book.authors = ['James Clear'] | |
page = urllib2.urlopen('http://jamesclear.com/articles').read() | |
soup = BeautifulSoup(page) | |
soup.prettify() | |
articles = soup.findAll('div', {'class':"archive-day-row"}) | |
sections = [] | |
for article in articles: | |
link = article.findAll('a')[0] | |
sections.append(addSection(link['href'], link.text)) | |
book.sections = sections | |
book.make(book.title) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment