Move WebcomicFactory in its own module.

Also, add an updater script for it.
This commit is contained in:
Tobias Gruetzmacher 2016-04-03 21:31:56 +02:00
parent bb1f20d867
commit 2c6decb7f5
4 changed files with 228 additions and 38 deletions

View file

@ -0,0 +1,144 @@
# -*- coding: utf-8 -*-
# Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs
# Copyright (C) 2012-2014 Bastian Kleineidam
# Copyright (C) 2015-2016 Tobias Gruetzmacher
from __future__ import absolute_import, division, print_function
from .common import _WordPressScraper
class _WebcomicFactory(_WordPressScraper):
latestSearch = '//a[contains(concat(" ", @class, " "), " comic-nav-last ")]'
@classmethod
def starter(cls):
"""this is basically helpers.indirectStarter, but dynamically selecting
the right parameters."""
data = cls.getPage(cls.firstStripUrl)
return cls.fetchUrl(cls.firstStripUrl, data, cls.latestSearch)
# do not edit anything below since these entries are generated from
# scripts/update_plugins.sh
# DO NOT REMOVE
class AsTheMayoTurns(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/as-the-mayo-turns/'
class ComicBookMafia(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/comic-book-mafia/'
class Dealers(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/dealers-1-1998-was-the-year/'
class DigitalHobo(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/digital-hobo-1-its-a-living-kinda/'
class ECoastVsWCoast(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/east-coast-vs-west-coast-greetings-from-the-coasts/'
class GunCulture(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/gun-culture/'
class IHateMyKids(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/i-hate-my-kids/'
class InARelationship(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/in-a-relationship-3/'
class IntergalacticMedicalDoctor(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/intergalactic-medical-doctor/'
class JSchoolgirlsInLove(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/japanese-schoolgirls-in-love-1/'
class KingdomOfTheDwarves(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/kingdom-of-the-dwarves/'
class LesterCrenshawIsDead(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/lester-crenshaw-is-dead/'
class Millennials(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/millennials/'
class MiserableComedians(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/miserable-comedians-1-funny-because-its-sad/'
class OldeTymeGamer(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/olde-tyme-gamer-playing-injured/'
class PinJunkies(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/pin-junkies/'
class PostApocalypticNick(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/post-apocalyptic-nick/'
class RealTalk(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/real-talk-people-who-cut-in-line/'
class SoManyNightmares(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/so-many-nightmares-freedom-nightmare/'
class SportsGuys(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/sports-guys/'
class TalesOfPizza(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/tales-of-pizza-bad-tipper/'
class TAndA(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/the-webcomic-factory-premiere-t-and-a/'
class TheAntiwarComic(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/the-antiwar-comic-the-party/'
class TheGentlemensClub(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/the-gentlemens-club/'
class TheHorrorOfColony6(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/the-horror-of-colony-6-page-1/'
class TheKingsOfViralVideo(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/the-kings-of-viral-video-premiere/'
class TheSharonAndTonyExperiment(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/the-sharon-and-tony-experiment/'
class TonyDestructo(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/tony-destructo/'
class WeirdBikerTales(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/weird-biker-tales-the-last-outlaw/'
class WillysSpaceDive(_WebcomicFactory):
firstStripUrl = 'http://www.thewebcomicfactory.com/comic/willys-space-dive/'

View file

@ -37,39 +37,3 @@ for (name, linkNumber) in [
add(name, 'http://www.flowerlarkstudios.com/',
starter=indirectStarter('http://www.flowerlarkstudios.com/',
'(//div[@id="sidebar-left"]//a)[' + str(linkNumber) + ']'))
# all comics on the webcomic factory
for (name, url) in [
('AntiwarComic', 'the-antiwar-comic-the-party/'),
('AstheMayoTurns', 'as-the-mayo-turns/'),
('ComicBookMafia', 'comic-book-mafia/'),
('Dealers', 'dealers-1-1998-was-the-year/'),
('DigitalHobo', 'digital-hobo-1-its-a-living-kinda/'),
('EastCoastVsWestCoast', 'east-coast-vs-west-coast-greetings-from-the-coasts/'),
('GunCulture', 'gun-culture/'),
('IHateMyKids', 'i-hate-my-kids/'),
('InARelationship', 'in-a-relationship-3/'),
('JapaneseSchoolgirlsinLove', 'japanese-schoolgirls-in-love-1/'),
('KingdomoftheDwarves', 'kingdom-of-the-dwarves/'),
('LesterCrenshawisDead', 'lester-crenshaw-is-dead/'),
('Millennials', 'millennials/'),
('MiserableComedians', 'miserable-comedians-1-funny-because-its-sad/'),
('OldeTymeGamer', 'olde-tyme-gamer-playing-injured/'),
('PinJunkies', 'pin-junkies/'),
('PostApocalypticNick', 'post-apocalyptic-nick/'),
('RealTalk', 'real-talk-people-who-cut-in-line/'),
('SoManyNightmares', 'so-many-nightmares-freedom-nightmare/'),
('SportsGuys', 'sports-guys/'),
('TalesOfPizza', 'tales-of-pizza-bad-tipper/'),
('TheGentlemensClub', 'the-gentlemens-club/'),
('TheHorrorOfColony6', 'the-horror-of-colony-6-page-1/'),
('TheKingsofViralVideo', 'the-kings-of-viral-video-premiere/'),
('TheSharonandTonyExperiment', 'the-sharon-and-tony-experiment/'),
('TonyDestructo', 'tony-destructo/'),
('WeirdBikerTales', 'weird-biker-tales-the-last-outlaw/'),
('WillysSpaceDive', 'willys-space-dive/')
]:
add(name, 'http://www.thewebcomicfactory.com',
starter=indirectStarter('http://www.thewebcomicfactory.com/comic/' + url,
"//a[contains(concat(' ', text(), ' '), ' Last ')]"))

View file

@ -1,6 +1,9 @@
# -*- coding: utf-8 -*-
# Copyright (C) 2012-2014 Bastian Kleineidam
# Copyright (C) 2016 Tobias Gruetzmacher
# Copyright (C) 2015-2016 Tobias Gruetzmacher
from __future__ import absolute_import, division, print_function
import json
import codecs
@ -42,6 +45,6 @@ def truncate_name(text):
def format_name(text):
"""Format a comic name."""
name = unescape(text)
name = "".join(capfirst(x) for x in name.split(" "))
name = asciify(name.replace(u'&', u'And').replace(u'@', u'At'))
name = capfirst(name)
return name

79
scripts/webcomicfactory.py Executable file
View file

@ -0,0 +1,79 @@
#!/usr/bin/env python
# Copyright (C) 2015-2016 Tobias Gruetzmacher
"""
Script to get WebComicFactory comics and save the info in a JSON file for
further processing.
"""
from __future__ import absolute_import, division, print_function
import codecs
import sys
import os
import requests
from lxml import html
sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..")) # noqa
from dosagelib.util import getPageContent
from scriptutil import (save_result, load_result, truncate_name, format_name)
json_file = __file__.replace(".py", ".json")
def find_first(session, url):
try:
data = html.document_fromstring(getPageContent(url, session))
data.make_links_absolute(url)
except IOError as msg:
print("ERROR:", msg, file=sys.stderr)
return url
firstlinks = data.cssselect('a.comic-nav-first')
if not firstlinks:
print("INFO No first link on »%s«, already first page?" % (url))
return url
return firstlinks[0].attrib['href']
def get_results():
"""Parse start page for supported comics."""
res = {}
url = 'http://www.thewebcomicfactory.com/'
session = requests.Session()
try:
data = html.document_fromstring(getPageContent(url, session))
data.make_links_absolute(url)
except IOError as msg:
print("ERROR:", msg, file=sys.stderr)
return {}
for comicdiv in data.cssselect('div.ceo_thumbnail_widget'):
comicname = comicdiv.cssselect('h2')[0]
comiclink = comicdiv.cssselect('a')[0]
comicurl = comiclink.attrib['href']
name = format_name(comicname.text)
if 'comic-color-key' in comicurl:
continue
comicurl = find_first(session, comicurl)
res[name] = comicurl
save_result(res, json_file)
def first_lower(x):
return x[0].lower()
def print_results(args):
"""Print all comics."""
min_comics, filename = args
with codecs.open(filename, 'a', 'utf-8') as fp:
data = load_result(json_file)
for name, url in sorted(data.items(), key=first_lower):
fp.write(u"\n\nclass %s(_WebcomicFactory):\n firstStripUrl = %r\n" % (
truncate_name(name), str(url)))
if __name__ == '__main__':
if len(sys.argv) > 1:
print_results(sys.argv[1:])
else:
get_results()