aly / netflix.py

""" Example usage: >>> netflix("60024942") (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'}) ID could be obtained through trivial URL parsing using any stdlib library. """ def netflix(id): """ Returns a tuple of strings: (title, year, date-published, MPAA-rating, duration, boxart-url, description, moreinfo) moreinfo may contain genre, language, actor and director info, depending on what's available""" soup = Soup(requests.get("http://www.netflix.com/JSON/BOB?movieid=" + id).json()["html"]) data = ( soup.find(attrs={'class': 'title'}).text.strip() if soup.find(attrs={'class': 'title'}) else None, soup.find(attrs={'class': 'year'}).text.strip() if soup.find(attrs={'class': 'year'}) else None, soup.find(attrs={'itemprop': 'datePublished'})["content"] if soup.find(attrs={'itemprop': 'datePublished'}) else None, soup.find(attrs={'class': 'mpaaRating'}).text.strip() if soup.find(attrs={'class': 'mpaaRating'}) else None, soup.find(attrs={'class': 'duration'}).text.strip() if soup.find(attrs={'class': 'duration'}) else None, soup.find(attrs={'itemprop': 'thumbnailUrl'})["src"] if soup.find(attrs={'itemprop': 'thumbnailUrl'}) else None, soup.find(attrs={'class', 'boxShot'}).nextSibling.strip(), {k.text.strip()[:-1].lower(): " ".join(v.text.strip().split()) for k,v in zip(soup.findAll('dt'), soup.findAll('dd'))} ) return data