def leech(url, filename=None):
# we have: a page, which could be absolutely any part of a story, or not a story at all
# check a bunch of things which are completely ff.n specific, to get text from it
site = _get_site(url)
if not site:
raise Exception("No site handler found")
story = site.extract(url, fetch)
if not story:
raise Exception("Couldn't extract story")
metadata = {
'title': story['title'],
'author': story['author'],
'unique_id': url,
}
html = []
for i, chapter in enumerate(story['chapters']):
html.append((chapter[0], 'chapter%d.html' % (i + 1), html_template.format(title=chapter[0], text=chapter[1])))
filename = filename or story['title'] + '.epub'
epub.make_epub(filename, html, metadata)
return filename
def leech(url, session, filename=None, args=None):
# we have: a page, which could be absolutely any part of a story, or not a story at all
# check a bunch of things which are completely ff.n specific, to get text from it
site, url = sites.get(url)
if not site:
raise Exception("No site handler found")
print("Handler", site, url)
handler = site(session, args=args)
with open('leech.json') as store_file:
store = json.load(store_file)
login = store.get('logins', {}).get(site.__name__, False)
if login:
handler.login(login)
story = handler.extract(url)
if not story:
raise Exception("Couldn't extract story")
dates = list(story.dates())
metadata = {
'title': story.title,
'author': story.author,
'unique_id': url,
'started': min(dates),
'updated': max(dates),
}
# The cover is static, and the only change comes from the image which we generate
html = [('Cover', 'cover.html', cover_template)]
cover_image = ('images/cover.png',
cover.make_cover(story.title,
story.author).read(), 'image/png')
html.append(('Front Matter', 'frontmatter.html',
frontmatter_template.format(now=datetime.datetime.now(),
**metadata)))
html.extend(chapter_html(story))
css = (
'Styles/base.css',
session.get(
'https://raw.githubusercontent.com/mattharrison/epub-css-starter-kit/master/css/base.css'
).text, 'text/css')
filename = filename or story.title + '.epub'
# print([c[0:-1] for c in html])
filename = epub.make_epub(filename,
html,
metadata,
extra_files=(css, cover_image))
return filename
def leech(url, session, filename=None, args=None):
# we have: a page, which could be absolutely any part of a story, or not a story at all
# check a bunch of things which are completely ff.n specific, to get text from it
site = sites.get(url)
if not site:
raise Exception("No site handler found")
handler = site(session, args=args)
with open('leech.json') as store_file:
store = json.load(store_file)
login = store.get('logins', {}).get(site.__name__, False)
if login:
handler.login(login)
story = handler.extract(url)
if not story:
raise Exception("Couldn't extract story")
dates = list(story.dates())
metadata = {
'title': story.title,
'author': story.author,
'unique_id': url,
'started': min(dates),
'updated': max(dates),
}
# The cover is static, and the only change comes from the image which we generate
html = [('Cover', 'cover.html', cover_template)]
cover_image = ('images/cover.png', cover.make_cover(story.title, story.author).read(), 'image/png')
html.append(('Front Matter', 'frontmatter.html', frontmatter_template.format(now=datetime.datetime.now(), **metadata)))
html.extend(chapter_html(story))
css = ('Styles/base.css', session.get('https://raw.githubusercontent.com/mattharrison/epub-css-starter-kit/master/css/base.css').text, 'text/css')
filename = filename or story.title + '.epub'
# print([c[0:-1] for c in html])
filename = epub.make_epub(filename, html, metadata, extra_files=(css, cover_image))
return filename