Download daily comics from comics.com and ucomics/gocomics.com e.g. peanuts, dilbert, calvin & hobbes etc.
Python, 167 lines
Download
Copy to clipboard1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 | '''
comixGetter.py - a python script to download daily comics from ucomics and comics .com's
author: sami
date: mar 07
todo: a. check if file already exists, b. save with correct file extension
'''
import httplib, re
re_date = '[a-zA-Z]+,\s+(\d+)\s+([a-zA-Z]+)\s+(\d+).+'
dates = {'Jan':'01', 'Feb':'02', 'Mar':'03', 'Apr':'04', 'May':'05', 'Jun':'06',
'Jul':'07', 'Aug':'08', 'Sep':'09', 'Oct':'10', 'Nov':'11', 'Dec':'12'}
comics_dot_com_info = (
('peanuts', '/comics/', '.+(\/comics\/peanuts\/archive\/images\/peanuts\d+\.gif|\/comics\/peanuts\/archive\/images\/peanuts\d+\.jpg).+'),
('dilbert', '/comics/', '.+(\/comics\/dilbert\/archive\/images\/dilbert\d+\.gif|\/comics\/dilbert\/archive\/images\/dilbert\d+\.jpg).+'),
('bignate', '/comics/', '.+(\/comics\/bignate\/archive\/images\/bignate\d+\.gif|\/comics\/bignate\/archive\/images\/bignate\d+\.jpg).+'),
('drabble', '/comics/', '.+(\/comics\/drabble\/archive\/images\/drabble\d+\.gif|\/comics\/drabble\/archive\/images\/drabble\d+\.jpg).+'),
('franknernest', '/comics/', '.+(\/comics\/franknernest\/archive\/images\/franknernest\d+\.jpg).+'),
('monty', '/comics/', '.+(\/comics\/monty\/archive\/images\/monty\d+\.gif|\/comics\/monty\/archive\/images\/monty\d+\.jpg).+'),
('wizardofid', '/creators/', '.+(\/creators\/wizardofid\/archive\/images\/wizardofid\d+\.gif|\/creators\/wizardofid\/archive\/images\/wizardofid\d+\.jpg).+'),
)
ucomics_dot_com_info = (
('doonesbury', '/comics/db/', 'db'),
('calvin_and_hobbes', '/comics/ch/', 'ch')
)
#===============================
#download_others - random comic downloads
#
#===============================
def download_others():
cnxn = connect('www.archiecomics.com')
print "getting: Archie"
cnxn.request("GET", '/')
res = cnxn.getresponse()
p = re.match(re_date, res.getheader("date"))
comic_path = '/pops_shop/dailycomics/image' + p.group(1) + '.gif'
#reconnecting since archiecomics.com closes connection after sending response
cnxn = connect('www.archiecomics.com')
cnxn.request("GET", comic_path)
res = cnxn.getresponse()
igot = res.status, res.reason
if res.status != "200" and res.reason != "OK":
print 'continuing to next comic since i got: '
print igot
return
f = open('archie'+"_"+p.group(1)+"_"+p.group(2)+"_"+p.group(3)+".gif", "wb")
f.write(res.read())
f.close()
print "OK"
#===============================
#connect(server) - connect to server
#
#===============================
def connect(server):
con = httplib.HTTPConnection(server, 80)
con.connect()
#print con
return con
#===============================
#download_ucomics_dot_com - download comics from ucomics/gocomics servers
#
#===============================
def download_ucomics_dot_com():
cnxn = connect('images.ucomics.com')
cnxn.request("GET", '/')
res = cnxn.getresponse()
p = re.match(re_date, res.getheader("date"))
for entry in ucomics_dot_com_info:
print "getting: " + entry[0]
comic_path = entry[1] + p.group(3) + '/'+ entry[2] + p.group(3)[2] + p.group(3)[3] + dates[p.group(2)] + p.group(1) + '.gif';
#for ucomics.com, we need to reconnect everytime, server closes connection after sending a response
cnxn = connect('images.ucomics.com')
cnxn.request("GET", comic_path)
res = cnxn.getresponse()
igot = res.status, res.reason
if res.status != "200" and res.reason != "OK":
print 'continuing to next comic since i got: '
print igot
continue
f = open(entry[0]+"_"+p.group(1)+"_"+p.group(2)+"_"+p.group(3)+".gif", "wb")
f.write(res.read())
f.close()
print "OK"
#===============================
#download_comics_dot_com - download comics from comics.com servers
#
#===============================
def download_comics_dot_com():
#Calling connect to url directly since for comics.com, the server does not close the connection itself after
#sending a response
cnxn = connect('comics.com')
for entry in comics_dot_com_info:
print "getting: " + entry[0]
cnxn.request("GET", entry[1]+entry[0]+'/')
res = cnxn.getresponse()
igot = res.status, res.reason
if res.status != "200" and res.reason != "OK":
print 'continuing to next comic since i got: '
print igot
continue
p = re.match(re_date, res.getheader("date"))
iread = res.read()
l = re.findall(entry[2], iread)
cnxn.request("GET", l[0])
res = cnxn.getresponse()
f = open(entry[0]+"_"+p.group(1)+"_"+p.group(2)+"_"+p.group(3)+".gif", "wb")
f.write(res.read())
f.close()
print "OK"
#===============================
#execution
#
#===============================
download_comics_dot_com()
download_ucomics_dot_com()
download_others()
|
Why use this: Instead of going to each website and reading comics one by one, use this script to download 'today's' comics - for your own particular comic, just add the regular expression to "comics_dot_com_info" or "ucomics_dot_com_info"
Known issues: Always saves files with .gif extension - Will not work if the server changes it's comics' regex - does not check if file already exists
Tags: web
