netflix.py
                        
                             · 2.1 KiB · Python
                        
                    
                    
                      
                        Raw
                      
                      
                        
                          
                        
                    
                    
                
                
            """
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.
Here, i'll do an example:
    from urlparse import urlparse, parse_qs # urllib.parse in python 3
    parse_qs(urlparse("http://www.netflix.com/WiPlayer?movieid=60024942").query)
    => {'movieid': ['60024942']}
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
"""
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
                | 1 | """ | 
| 2 | Example usage: | 
| 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 | |
| 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 | 
| 15 | """ | 
| 16 | |
| 17 | def netflix(id): | 
| 18 | """ Returns a tuple of strings: (title, year, date-published, MPAA-rating, duration, boxart-url, description, moreinfo) | 
| 19 | moreinfo may contain genre, language, actor and director info, depending on what's available""" | 
| 20 | soup = Soup(requests.get("http://www.netflix.com/JSON/BOB?movieid=" + id).json()["html"]) | 
| 21 | data = ( | 
| 22 | soup.find(attrs={'class': 'title'}).text.strip() if soup.find(attrs={'class': 'title'}) else None, | 
| 23 | soup.find(attrs={'class': 'year'}).text.strip() if soup.find(attrs={'class': 'year'}) else None, | 
| 24 | soup.find(attrs={'itemprop': 'datePublished'})["content"] if soup.find(attrs={'itemprop': 'datePublished'}) else None, | 
| 25 | soup.find(attrs={'class': 'mpaaRating'}).text.strip() if soup.find(attrs={'class': 'mpaaRating'}) else None, | 
| 26 | soup.find(attrs={'class': 'duration'}).text.strip() if soup.find(attrs={'class': 'duration'}) else None, | 
| 27 | soup.find(attrs={'itemprop': 'thumbnailUrl'})["src"] if soup.find(attrs={'itemprop': 'thumbnailUrl'}) else None, | 
| 28 | soup.find(attrs={'class', 'boxShot'}).nextSibling.strip(), | 
| 29 | {k.text.strip()[:-1].lower(): " ".join(v.text.strip().split()) for k,v in zip(soup.findAll('dt'), soup.findAll('dd'))} | 
| 30 | ) | 
| 31 | return data | 
| 32 |