first commitHEADmaster

1 files changed, 93 insertions, 0 deletions

diff --git a/carnoon.py b/carnoon.py
new file mode 100755
index 0000000..45f98af
--- /dev/null
+++ b/carnoon.py
@@ -0,0 +1,93 @@
+#/usr/bin/python2
+
+import urllib2
+import random
+import Image
+import os.path
+import re
+
+class Comic(object):
+    def __init__(self, comicurl, filenformat, updateurl, updatere):
+        self.comicurl = comicurl
+        self.filenformat = filenformat
+        self.updateurl = updateurl
+        self.updatere = updatere
+        self.last = 0
+
+    def update_last(self):
+        opener = urllib2.build_opener()
+        opener.addheaders = [('User-agent', 'Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko')]
+
+        url = opener.open(self.updateurl)
+        data = url.read()
+        url.close()
+
+        result = re.search(self.updatere, data).group('link') # search for last image link
+
+        if(not result.startswith('http')):
+                result = self.comicurl + result
+        
+        self.last = int(re.search(r'(?P<id>\d+)\.(?i)(jpg|png|gif|bmp)$', result).group('id')) # get file name's content before '.'
+
+    def get_link(self, number = -1):
+        opener = urllib2.build_opener() # for a UA
+        opener.addheaders = [('User-agent', 'Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko')]
+
+        if(number == -1):
+            urlstr = self.randomurl
+        else:
+            urlstr = self.comicurl + (self.filenformat % number)
+
+        filere = re.compile(r'.*?[^\s/]+\.(?i)(jpg|png|gif|bmp)$')
+        if(filere.match(urlstr)):
+            return urlstr
+
+        url = opener.open(urlstr)
+
+        data = url.read() # download web page
+        url.close()
+
+        result = re.search(self.updatere, data) # search for image link
+
+        if(result):
+            return result.group('link')
+        else:
+            print "Please check your regular expression: no matches found"
+            return None
+
+    def display_random(self):
+        # urlstr: url
+        # picstr: random number; appended to url
+        # pref: prefix for file name; e.g. Comics/xkcd/
+        # srcre: regular expression in case url + picstr is not a direct link
+
+        urlstr = self.get_link(random.randrange(0, self.last)) # get direct image download link by RE
+
+        fname = "Comics/" + self.comicurl.replace("http://", "").replace("/", "") + int(re.search(r'(?P<id>\d+)\.(?i)(jpg|png|gif|bmp)$', result).group('id'))
+
+        opener = urllib2.build_opener() # for a UA
+        opener.addheaders = [('User-agent', 'Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko')]
+
+        directory = "Comics/"
+        if not os.path.exists(directory): # create subdirectory if needed
+            os.makedirs(directory)
+
+        if not os.path.isfile(fname):
+            # download picture and open if not done yet
+            url = opener.open(urlstr)
+            data = url.read()
+            url.close()
+
+            pic = open(fname, 'w')
+            pic.write(data)
+            pic.close()
+
+        Image.open(fname).show()
+
+ruthe = Comic("http://ruthe.de/cartoons/", "strip_%d.jpg", "http://ruthe.de", r'<img src="(?P<link>.*?)" alt="Cartoon" border="0" />')
+ruthe.update_last()
+ruthe.display_random()
+
+xkcd = Comic("xkcd.com", "imgs.%s.com/comics/", r'Permanent link to this comic: (?P<link>.*?)')
+xkcd.update_last()
+xkcd.display_random("/1/")