2012-11-28 17:15:12 +00:00
|
|
|
#!/usr/bin/env python
|
2013-01-09 21:21:19 +00:00
|
|
|
# Copyright (C) 2012-2013 Bastian Kleineidam
|
2012-11-28 17:15:12 +00:00
|
|
|
"""
|
2012-12-12 16:41:29 +00:00
|
|
|
Script to get a list of gocomics and save the info in a JSON file for further processing.
|
2012-11-28 17:15:12 +00:00
|
|
|
"""
|
|
|
|
from __future__ import print_function
|
|
|
|
import re
|
|
|
|
import sys
|
|
|
|
import os
|
2013-02-12 20:53:57 +00:00
|
|
|
import requests
|
2012-11-28 17:15:12 +00:00
|
|
|
sys.path.append(os.path.join(os.path.dirname(__file__), ".."))
|
|
|
|
from dosagelib.util import tagre, getPageContent, asciify, unescape
|
2013-01-09 21:20:03 +00:00
|
|
|
from scriptutil import contains_case_insensitive, capfirst, save_result, load_result, truncate_name
|
2012-11-28 17:15:12 +00:00
|
|
|
|
|
|
|
json_file = __file__.replace(".py", ".json")
|
|
|
|
|
|
|
|
#<a href="/shortname" class="alpha_list updated">name</a>
|
|
|
|
url_matcher = re.compile(tagre("a", "href", r'(/[^"]+)', after="alpha_list") + r"([^<]+)</a>")
|
|
|
|
|
2012-11-29 05:46:58 +00:00
|
|
|
# names of comics to exclude
|
|
|
|
exclude_comics = [
|
2013-04-28 17:58:38 +00:00
|
|
|
"Adagio", # too few comics
|
2013-04-04 16:30:02 +00:00
|
|
|
"AgentGates", # too few comics
|
2012-12-04 06:02:40 +00:00
|
|
|
"Apocalypseharry", # too few comics
|
|
|
|
"BatkidandBatrat", # too few comics
|
|
|
|
"BETWEENTHELINES", # comic unavailable
|
|
|
|
"Bonner", # missing page
|
|
|
|
"Buster", # comic unavailabe
|
2013-03-07 18:54:18 +00:00
|
|
|
"CarteBlanche", # missing images
|
2013-04-28 17:58:38 +00:00
|
|
|
"CountyLine", # too few comics
|
2012-12-04 06:02:40 +00:00
|
|
|
"DALTONDOG", # comic unavailable
|
|
|
|
"DellAndSteve", # too few comics
|
|
|
|
"Dilbert", # redirect
|
2013-02-26 05:12:46 +00:00
|
|
|
"DutchnPals", # too few comics
|
2013-03-07 22:08:17 +00:00
|
|
|
"EclecticCartoons", # missing images
|
2013-03-07 17:22:24 +00:00
|
|
|
"FlexandTone", # too few comics
|
2013-03-07 22:08:17 +00:00
|
|
|
"FrikkFrakkAndFrank", # too few comics
|
2013-04-04 16:30:02 +00:00
|
|
|
"GOODAndEVIL", # too few comics
|
2013-04-28 17:58:38 +00:00
|
|
|
"GoodwithCoffee", # too few comics
|
2012-12-04 06:02:40 +00:00
|
|
|
"InkeeDoodles", # comic unavailable
|
2013-04-04 16:30:02 +00:00
|
|
|
"KALEECHIKORNERS", # too few comics
|
2013-04-11 16:27:43 +00:00
|
|
|
"LoveIs", # missing images
|
2012-12-04 06:02:40 +00:00
|
|
|
"MaggiesComics", # too few comics
|
|
|
|
"OfMiceandMud", # too few comics
|
|
|
|
"OysterWar", # too few comics
|
2013-04-28 17:58:38 +00:00
|
|
|
"Penguins", # too few comics
|
2012-12-04 06:02:40 +00:00
|
|
|
"PIGTIMES", # comic unavailable
|
|
|
|
"PS", # comic unavailable
|
2013-04-04 16:30:02 +00:00
|
|
|
"Radiowave", # too few comics
|
2013-03-26 16:33:15 +00:00
|
|
|
"RatchetAndSpin", # too few comics
|
2012-12-07 23:45:18 +00:00
|
|
|
"RichardsPoorAlmanac", # missing images
|
2012-12-04 06:02:40 +00:00
|
|
|
"SherpaAid", # comic unavailable
|
2013-02-26 05:12:46 +00:00
|
|
|
"Slowpoke", # comic moved
|
2013-04-04 16:30:02 +00:00
|
|
|
"SpaghettiSandwich", # too few comics
|
2012-12-04 06:02:40 +00:00
|
|
|
"SparComics", # comic unavailable
|
2012-12-13 20:05:27 +00:00
|
|
|
"SurvivingSingle", # comic unavailable
|
2013-04-04 16:30:02 +00:00
|
|
|
"TheDeadlys", # too few comics
|
2013-04-28 17:58:38 +00:00
|
|
|
"Tomversation", # too few comics
|
2013-03-07 22:08:17 +00:00
|
|
|
"VoicesInTheDark", # too few comics
|
2013-02-23 08:07:44 +00:00
|
|
|
"WhatTheFrak", # too few comics
|
|
|
|
"ZeekyZebraandCompany", # too few comics
|
2012-11-29 05:46:58 +00:00
|
|
|
]
|
|
|
|
|
2012-11-28 17:15:12 +00:00
|
|
|
|
2013-02-12 20:53:57 +00:00
|
|
|
def handle_url(url, session, res):
|
2012-11-28 17:15:12 +00:00
|
|
|
"""Parse one search result page."""
|
|
|
|
print("Parsing", url, file=sys.stderr)
|
|
|
|
try:
|
2013-02-12 20:53:57 +00:00
|
|
|
data, baseUrl = getPageContent(url, session)
|
2012-11-28 17:15:12 +00:00
|
|
|
except IOError as msg:
|
|
|
|
print("ERROR:", msg, file=sys.stderr)
|
|
|
|
return
|
|
|
|
for match in url_matcher.finditer(data):
|
|
|
|
shortname = match.group(1)
|
|
|
|
name = unescape(match.group(2))
|
|
|
|
name = asciify(name.replace('&', 'And').replace('@', 'At'))
|
2012-12-12 16:41:29 +00:00
|
|
|
name = capfirst(name)
|
2012-11-29 05:46:58 +00:00
|
|
|
if name in exclude_comics:
|
|
|
|
continue
|
2012-11-28 17:15:12 +00:00
|
|
|
if contains_case_insensitive(res, name):
|
|
|
|
# we cannot handle two comics that only differ in case
|
2013-03-12 19:47:11 +00:00
|
|
|
print("INFO: skipping possible duplicate", repr(name), file=sys.stderr)
|
2012-11-28 17:15:12 +00:00
|
|
|
continue
|
|
|
|
res[name] = shortname
|
|
|
|
|
|
|
|
|
|
|
|
def get_results():
|
|
|
|
"""Parse all search result pages."""
|
|
|
|
# store info in a dictionary {name -> shortname}
|
|
|
|
res = {}
|
2013-02-12 20:53:57 +00:00
|
|
|
session = requests.Session()
|
|
|
|
handle_url('http://www.gocomics.com/features', session, res)
|
|
|
|
handle_url('http://www.gocomics.com/explore/editorial_list', session, res)
|
|
|
|
handle_url('http://www.gocomics.com/explore/sherpa_list', session, res)
|
2012-12-19 19:42:53 +00:00
|
|
|
save_result(res, json_file)
|
2012-11-28 17:15:12 +00:00
|
|
|
|
|
|
|
|
|
|
|
def print_results(args):
|
|
|
|
"""Print all comics that have at least the given number of minimum comic strips."""
|
2012-12-19 19:42:53 +00:00
|
|
|
for name, shortname in sorted(load_result(json_file).items()):
|
2012-11-29 05:46:58 +00:00
|
|
|
if name in exclude_comics:
|
|
|
|
continue
|
2013-04-25 19:50:45 +00:00
|
|
|
print("add(%r, %r)" % (str(truncate_name(name)), str(shortname)))
|
2012-11-28 17:15:12 +00:00
|
|
|
|
|
|
|
|
|
|
|
if __name__ == '__main__':
|
|
|
|
if len(sys.argv) > 1:
|
|
|
|
print_results(sys.argv[1:])
|
|
|
|
else:
|
|
|
|
get_results()
|