svn.andrew.net.au/scripts/movies.py

#!/usr/bin/python

from sgmllib import SGMLParser
import htmlentitydefs
import urllib
import time
import datetime
import xml.sax.saxutils

class BaseHTMLProcessor(SGMLParser):

        def reset(self):
                self.pieces = []
                self.include = False
                self.nestlevel = 0
                SGMLParser.reset(self)

        def unknown_starttag(self, tag, attrs):
                strattrs = "".join([' %s="%s"' % (key, value) for key, value in attrs])
                if tag == "table":
                        #print "Saw a table"
                        if 'class' in attrs[0] and 'movies' in attrs[0]:
                                self.include = True
                        if self.include:
                                self.nestlevel += 1

                if self.include:
                        self.pieces.append("<%(tag)s%(strattrs)s>" % locals())
                        

        def unknown_endtag(self, tag):
                if self.include:
                        self.pieces.append("</%(tag)s>" % locals())
                        if tag == "table":
                                self.nestlevel -= 1
                                if self.nestlevel == 0:
                                        self.include = False


        def handle_charref(self, ref):
                if self.include:
                        self.pieces.append("&#%(ref)s;" % locals())

        def handle_entityref(self, ref):
                if self.include:
                        self.pieces.append("&%(ref)s" % locals())
                        if htmlentitydefs.entitydefs.has_key(ref):
                                self.pieces.append(";")

        def handle_data(self, text):
                if self.include:
                        self.pieces.append(text)

        def handle_comment(self, text):
                if self.include:
                        self.pieces.append("<!--%(text)s-->" % locals())

        def handle_pi(self, text):
                if self.include:
                        self.pieces.append("<?%(text)s>" % locals())

        def handle_decl(self, text):
                if self.include:
                        self.pieces.append("<!%(text)s>" % locals())

        def output(self):
                return "".join(self.pieces)


def main():
        parser = BaseHTMLProcessor()
        #html = open("index.html")
        html = urllib.urlopen("http://www.imdb.com/nowplaying/")
        parser.feed(html.read())
        html.close()
        movies = xml.sax.saxutils.escape(parser.output())
        #movies = parser.output()
        print """<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">

<link href="http://home.andrew.net.au/~apollock/movies.xml" rel="self"/>

<title>This week's movies from IMDb</title>
<updated>%(updated)sZ</updated>
<author>
        <name>Andrew Pollock</name>
</author>
<id>http://www.andrew.net.au/</id>

<entry>
<id>%(timestamp)s</id>

<updated>%(updated)sZ</updated>
<title>This week's movies</title>

<content type="html">
%(movies)s
</content>
</entry>
</feed>
""" % { 'updated': datetime.datetime.utcnow().isoformat()[0:19], 'movies': movies, 'timestamp': int(time.time()) }

if __name__ == "__main__":
        main()
1	#!/usr/bin/python
2
3	from sgmllib import SGMLParser
4	import htmlentitydefs
5	import urllib
6	import time
7	import datetime
8	import xml.sax.saxutils
9
10	class BaseHTMLProcessor(SGMLParser):
11
12	def reset(self):
13	self.pieces = []
14	self.include = False
15	self.nestlevel = 0
16	SGMLParser.reset(self)
17
18	def unknown_starttag(self, tag, attrs):
19	strattrs = "".join([' %s="%s"' % (key, value) for key, value in attrs])
20	if tag == "table":
21	#print "Saw a table"
22	if 'class' in attrs[0] and 'movies' in attrs[0]:
23	self.include = True
24	if self.include:
25	self.nestlevel += 1
26
27	if self.include:
28	self.pieces.append("<%(tag)s%(strattrs)s>" % locals())
29
30
31	def unknown_endtag(self, tag):
32	if self.include:
33	self.pieces.append("</%(tag)s>" % locals())
34	if tag == "table":
35	self.nestlevel -= 1
36	if self.nestlevel == 0:
37	self.include = False
38
39
40	def handle_charref(self, ref):
41	if self.include:
42	self.pieces.append("&#%(ref)s;" % locals())
43
44	def handle_entityref(self, ref):
45	if self.include:
46	self.pieces.append("&%(ref)s" % locals())
47	if htmlentitydefs.entitydefs.has_key(ref):
48	self.pieces.append(";")
49
50	def handle_data(self, text):
51	if self.include:
52	self.pieces.append(text)
53
54	def handle_comment(self, text):
55	if self.include:
56	self.pieces.append("<!--%(text)s-->" % locals())
57
58	def handle_pi(self, text):
59	if self.include:
60	self.pieces.append("<?%(text)s>" % locals())
61
62	def handle_decl(self, text):
63	if self.include:
64	self.pieces.append("<!%(text)s>" % locals())
65
66	def output(self):
67	return "".join(self.pieces)
68
69
70	def main():
71	parser = BaseHTMLProcessor()
72	#html = open("index.html")
73	html = urllib.urlopen("http://www.imdb.com/nowplaying/")
74	parser.feed(html.read())
75	html.close()
76	movies = xml.sax.saxutils.escape(parser.output())
77	#movies = parser.output()
78	print """<?xml version="1.0" encoding="utf-8"?>
79	<feed xmlns="http://www.w3.org/2005/Atom">
80
81	<link href="http://home.andrew.net.au/~apollock/movies.xml" rel="self"/>
82
83	<title>This week's movies from IMDb</title>
84	<updated>%(updated)sZ</updated>
85	<author>
86	<name>Andrew Pollock</name>
87	</author>
88	<id>http://www.andrew.net.au/</id>
89
90	<entry>
91	<id>%(timestamp)s</id>
92
93	<updated>%(updated)sZ</updated>
94	<title>This week's movies</title>
95
96	<content type="html">
97	%(movies)s
98	</content>
99	</entry>
100	</feed>
101	""" % { 'updated': datetime.datetime.utcnow().isoformat()[0:19], 'movies': movies, 'timestamp': int(time.time()) }
102
103	if __name__ == "__main__":
104	main()