1
0
Fork 0
mirror of https://github.com/kemayo/leech synced 2025-12-15 21:05:59 +01:00

Switch from using raw argparser to using click. Preserves the existing

interface, except leech --flush becomes leech flush
This commit is contained in:
Will Oursler 2017-10-07 13:01:44 -04:00
parent 8ac1aa8bb0
commit db48233cf4
5 changed files with 98 additions and 84 deletions

View file

@ -19,10 +19,20 @@ My recommended setup process is:
Usage
---
Basic
$ python3 leech.py [[URL]]
A new file will appear named `Title of the Story.epub`.
This is equivalent to the slightly longer
$ python3 leech.py download [[URL]]
Flushing the cache
$ python3 leech.py flush
If you want to put it on a Kindle you'll have to convert it. I'd recommend [Calibre](http://calibre-ebook.com/), though you could also try using [kindlegen](http://www.amazon.com/gp/feature.html?docId=1000765211) directly.
Supports

140
leech.py
View file

@ -1,79 +1,99 @@
#!/usr/bin/env python
#!/usr/bin/env python3
import argparse
import sys
import json
import click
from click_default_group import DefaultGroup
import requests
import requests_cache
import http.cookiejar
import json
import sites
import ebook
import requests
import requests_cache
__version__ = 1
__version__ = 2
USER_AGENT = 'Leech/%s +http://davidlynch.org' % __version__
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")
def uses_session(command):
"""Decorator for click commands that need a session."""
@click.option('--cache/--no-cache', default=True)
def wrapper(cache, **kwargs):
if cache:
session = requests_cache.CachedSession('leech', expire_after=4 * 3600)
else:
session = requests.Session()
print("Handler", site, url)
lwp_cookiejar = http.cookiejar.LWPCookieJar()
try:
lwp_cookiejar.load('leech.cookies', ignore_discard=True)
except Exception as e:
pass
session.cookies = lwp_cookiejar
session.headers.update({
'User-agent': USER_AGENT
})
return command(session=session, **kwargs)
wrapper.__name__ = command.__name__
return wrapper
handler = site(session, args=args)
with open('leech.json') as config_file:
config = json.load(config_file)
def uses_story(command):
"""Decorator for click commands that need a story."""
@click.argument('url')
@click.option('--include-index', default=False, help='[Xenforo only] Should the chapter marked as an index be included?')
@click.option('--offset', type=int, default=None, help='[Xenforo only] The chapter to start from.')
@click.option('--limit', type=int, default=None, help='[Xenforo only] The chapter to end with.')
@click.option('--skip-spoilers/--include-spoilers', default=True, help='[Xenforo only] If the story should include content enclosed in spoiler tags.')
@uses_session
def wrapper(url, session, include_index, offset, limit, skip_spoilers, **kwargs):
site, url = sites.get(url)
if not site:
raise Exception("No site handler found")
login = config.get('logins', {}).get(site.__name__, False)
if login:
handler.login(login)
handler = site(session, options={
'offset': offset,
'limit': limit,
'skip_spoilers': skip_spoilers,
'include_index': include_index,
})
cover_options = config.get('cover', {})
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")
story = handler.extract(url)
if not story:
raise Exception("Couldn't extract story")
return ebook.generate_epub(story, filename, cover_options=cover_options)
command(story=story, **kwargs)
wrapper.__name__ = command.__name__
return wrapper
@click.group(cls=DefaultGroup, default='download', default_if_no_args=True)
def cli():
"""Top level click group. Uses click-default-group to preserve most behavior from leech v1."""
pass
@cli.command()
def flush():
""""Flushes the contents of the cache."""
requests_cache.install_cache('leech')
requests_cache.clear()
print("Flushed cache")
@cli.command()
@uses_story
def download(story):
"""Downloads a story and saves it on disk as a ebpub ebook."""
filename = ebook.generate_epub(story)
print("File created:", filename)
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('url', help="url of a story to fetch", nargs='?')
parser.add_argument('--filename', help="output filename (the title is used if this isn't provided)")
parser.add_argument('--no-cache', dest='cache', action='store_false')
parser.add_argument('--flush', dest='flush', action='store_true')
parser.set_defaults(cache=True, flush=False)
args, extra_args = parser.parse_known_args()
if args.flush:
requests_cache.install_cache('leech')
requests_cache.clear()
print("Flushed cache")
sys.exit()
if not args.url:
sys.exit("URL is required")
if args.cache:
session = requests_cache.CachedSession('leech', expire_after=4 * 3600)
else:
session = requests.Session()
lwp_cookiejar = http.cookiejar.LWPCookieJar()
try:
lwp_cookiejar.load('leech.cookies', ignore_discard=True)
except Exception as e:
pass
session.cookies = lwp_cookiejar
session.headers.update({
'User-agent': USER_AGENT
})
filename = leech(args.url, filename=args.filename, session=session, args=extra_args)
print("File created:", filename)
cli()

View file

@ -15,3 +15,5 @@ requests-cache==0.4.13
six==1.10.0
urllib3==1.22
webencodings==0.5.1
click==6.7
click-default-group==1.2

View file

@ -1,7 +1,6 @@
import glob
import os
import argparse
import uuid
import attr
from bs4 import BeautifulSoup
@ -62,11 +61,8 @@ class Site:
extracting the content of a story from said site.
"""
session = attr.ib()
args = attr.ib()
footnotes = attr.ib(default=attr.Factory(list), init=False)
def __attrs_post_init__(self):
self.options = self._parse_args(self.args)
options = attr.ib(default=attr.Factory(dict))
@staticmethod
def matches(url):
@ -88,14 +84,6 @@ class Site:
def login(self, login_details):
raise NotImplementedError()
def _parse_args(self, args):
parser = argparse.ArgumentParser()
self._add_arguments(parser)
return parser.parse_args(args)
def _add_arguments(self, parser):
pass
def _soup(self, url, method='html5lib', **kw):
page = self.session.get(url, **kw)
if not page:

View file

@ -40,7 +40,7 @@ class XenForo(Site):
mark for mark in self._chapter_list(url)
if '/members' not in mark.get('href') and '/threadmarks' not in mark.get('href')
]
marks = marks[self.options.offset:self.options.limit]
marks = marks[self.options['offset']:self.options['limit']]
for idx, mark in enumerate(marks, 1):
href = mark.get('href')
@ -95,7 +95,7 @@ class XenForo(Site):
if not links:
raise SiteException("No links in index?")
if self.options.include_index:
if self.options['include_index']:
fake_link = self._new_tag('a', href=url)
fake_link.string = "Index"
links.insert(0, fake_link)
@ -151,7 +151,7 @@ class XenForo(Site):
# spoilers don't work well, so turn them into epub footnotes
for idx, spoiler in enumerate(post.find_all(class_='ToggleTriggerAnchor')):
spoiler_title = spoiler.find(class_='SpoilerTitle')
if self.options.spoilers:
if self.options['skip_spoilers']:
link = self._footnote(spoiler.find(class_='SpoilerTarget').extract(), chapterid)
if spoiler_title:
link.string = spoiler_title.get_text()
@ -174,12 +174,6 @@ class XenForo(Site):
return datetime.datetime.strptime(maybe_date['title'], "%b %d, %Y at %I:%M %p")
raise SiteException("No date", maybe_date)
def _add_arguments(self, parser):
parser.add_argument('--include-index', dest='include_index', action='store_true', default=False)
parser.add_argument('--offset', dest='offset', type=int, default=None)
parser.add_argument('--limit', dest='limit', type=int, default=None)
parser.add_argument('--skip-spoilers', dest='spoilers', action='store_false', default=True)
class XenForoIndex(XenForo):
@classmethod
@ -198,8 +192,8 @@ class SpaceBattles(XenForo):
@register
class SpaceBattlesIndex(XenForoIndex):
domain = 'forums.spacebattles.com'
class SpaceBattlesIndex(SpaceBattles, XenForoIndex):
pass
@register