Created
December 20, 2011 14:20
-
-
Save dbrgn/1501715 to your computer and use it in GitHub Desktop.
Get list of films that most frequently use the word "fuck" and fetch the corresponding IMDB ratings.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # WARNING: Ugly hack. | |
| import re | |
| import requests | |
| from BeautifulSoup import BeautifulSoup | |
| import imdb | |
| print 'Getting data from Wikipedia...' | |
| # Request Wikipedia page | |
| r = requests.get('http://en.wikipedia.org/wiki/List_of_films_that_most_frequently_use_the_word_%22fuck%22') | |
| print 'Parsing HTML data...' | |
| # Fetch HTML table | |
| soup = BeautifulSoup(r.content) | |
| table = soup.find('table', {'class': 'wikitable sortable'}) | |
| rows = table.findAll('tr') | |
| # Parse HTML table | |
| keys = { | |
| 0: 'film', | |
| 1: 'year', | |
| 2: 'fuckcount', | |
| 3: 'minutes', | |
| 4: 'uses_per_minute', | |
| 5: 'source', | |
| 6: 'ref' | |
| } | |
| movies = [] | |
| for row in rows[1:]: | |
| rowmap = {} | |
| for i, field in enumerate(row.findAll('td')): | |
| if i == 2: | |
| text = re.sub(r'^([0-9]+).*', r'\1', field.text) | |
| else: | |
| text = field.text | |
| rowmap[keys[i]] = text | |
| movies.append(rowmap) | |
| # Fetch imdb data | |
| ia = imdb.IMDb() | |
| for movie in movies: | |
| search_result = ia.search_movie(movie['film']) | |
| print 'Fetching IMDB rating for movie %s...' % movie['film'] | |
| try: | |
| match = filter(lambda x: x['year'] == int(movie['year']), search_result)[0] | |
| ia.update(match) | |
| print 'Found match "%s (%s)" with rating %s.' % (match['title'], match['year'], match['rating']) | |
| movie['imdb_rating'] = match['rating'] | |
| except (IndexError, KeyError): | |
| movie['imdb_rating'] = None | |
| print 'Found no match.' | |
| pass | |
| print 'Exporting to HTML...' | |
| row_tpl = '<tr><td>%s</td><td>%s</td><td>%s</td><td>%s</td></tr>\n' | |
| rows = [] | |
| for movie in movies: | |
| rows.append(row_tpl % (movie['film'], movie['fuckcount'], movie['uses_per_minute'], movie['imdb_rating'])) | |
| table = '<table><tr><th>Movie</th><th>"Fuck" count</th><th>Uses/Minute</th><th>IMDB Rating</th></tr>%s</table>' % ''.join(rows) | |
| html = '<html><head><title>FCPM IMDB Ratings</title></head><body>%s</body></html>' % table | |
| outfile = open('data.html', 'w') | |
| outfile.write(html) | |
| outfile.close() | |
| print '...done.' | |
| print 'Exporting to JSON...' | |
| print '...not yet implemented.' | |
| print 'Done.' |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Note: Some of the years on the Wikipedia page seem to be wrong, so it won't fetch those ratings.