Revision of netflix.py

Steven Smith revised this gist 1427978860. Go to revision

1 file changed, 11 insertions, 2 deletions

netflix.py

			@@ -1,8 +1,17 @@
1	1		"""
2	2		Example usage:
3		-	>>> netflix("60024942")
4		-	(u'Catch Me If You Can', u'2002', u'Thu Jan 09 08:00:00 UTC 2003', u'M', u'140 minutes', u'http://cdn2.nflximg.net/images/0432/12050432.jpg', u'An FBI agent makes it his mission to put cunning con man Frank Abagnale Jr. behind bars. But Frank not only eludes capture, he revels in the pursuit.', {u'director': u'Steven Spielberg', u'genre': u'Dramas', u'language': u'English', u'starring': u'Leonardo DiCaprio, Tom Hanks'})
	3	+
	4	+	>>> netflix("60024942")
	5	+	(u'Catch Me If You Can', u'2002', u'Thu Jan 09 08:00:00 UTC 2003', u'M', u'140 minutes', u'http://cdn2.nflximg.net/images/0432/12050432.jpg', u'An FBI agent makes it his mission to put cunning con man Frank Abagnale Jr. behind bars. But Frank not only eludes capture, he revels in the pursuit.', {u'director': u'Steven Spielberg', u'genre': u'Dramas', u'language': u'English', u'starring': u'Leonardo DiCaprio, Tom Hanks'})
	6	+
5	7		ID could be obtained through trivial URL parsing using any stdlib library.
	8	+	Here, i'll do an example:
	9	+
	10	+	from urlparse import urlparse, parse_qs # urllib.parse in python 3
	11	+	parse_qs(urlparse("http://www.netflix.com/WiPlayer?movieid=60024942").query)
	12	+	=> {'movieid': ['60024942']}
	13	+
	14	+	Obviously you'd have a much longer url, but you can then use r["movieid"][0] to get the id, pass it to netflix(), tadaaaaa
6	15		"""
7	16
8	17		def netflix(id):

Steven Smith revised this gist 1427978316. Go to revision

1 file changed, 22 insertions

netflix.py(file created)

		@@ -0,0 +1,22 @@
1	+	"""
2	+	Example usage:
3	+	>>> netflix("60024942")
4	+	(u'Catch Me If You Can', u'2002', u'Thu Jan 09 08:00:00 UTC 2003', u'M', u'140 minutes', u'http://cdn2.nflximg.net/images/0432/12050432.jpg', u'An FBI agent makes it his mission to put cunning con man Frank Abagnale Jr. behind bars. But Frank not only eludes capture, he revels in the pursuit.', {u'director': u'Steven Spielberg', u'genre': u'Dramas', u'language': u'English', u'starring': u'Leonardo DiCaprio, Tom Hanks'})
5	+	ID could be obtained through trivial URL parsing using any stdlib library.
6	+	"""
7	+
8	+	def netflix(id):
9	+	""" Returns a tuple of strings: (title, year, date-published, MPAA-rating, duration, boxart-url, description, moreinfo)
10	+	moreinfo may contain genre, language, actor and director info, depending on what's available"""
11	+	soup = Soup(requests.get("http://www.netflix.com/JSON/BOB?movieid=" + id).json()["html"])
12	+	data = (
13	+	soup.find(attrs={'class': 'title'}).text.strip() if soup.find(attrs={'class': 'title'}) else None,
14	+	soup.find(attrs={'class': 'year'}).text.strip() if soup.find(attrs={'class': 'year'}) else None,
15	+	soup.find(attrs={'itemprop': 'datePublished'})["content"] if soup.find(attrs={'itemprop': 'datePublished'}) else None,
16	+	soup.find(attrs={'class': 'mpaaRating'}).text.strip() if soup.find(attrs={'class': 'mpaaRating'}) else None,
17	+	soup.find(attrs={'class': 'duration'}).text.strip() if soup.find(attrs={'class': 'duration'}) else None,
18	+	soup.find(attrs={'itemprop': 'thumbnailUrl'})["src"] if soup.find(attrs={'itemprop': 'thumbnailUrl'}) else None,
19	+	soup.find(attrs={'class', 'boxShot'}).nextSibling.strip(),
20	+	{k.text.strip()[:-1].lower(): " ".join(v.text.strip().split()) for k,v in zip(soup.findAll('dt'), soup.findAll('dd'))}
21	+	)
22	+	return data

Newer Older