dates, reduce number of imdb pages loaded

This commit is contained in:
j 2010-07-10 13:54:33 +02:00
commit f3147437b6
4 changed files with 16 additions and 8 deletions

View file

@ -26,7 +26,7 @@ class Imdb(SiteParser):
},
'cast': {
'page': 'fullcredits',
'page': 'combined',
're': [
'<td class="nm">.*?>(.*?)</a>.*?<td class="char">(.*?)</td>',
lambda ll: [stripTags(l) for l in ll]
@ -34,7 +34,7 @@ class Imdb(SiteParser):
'type': 'list'
},
'cinematographers': {
'page': 'fullcredits',
'page': 'combined',
're': [
lambda data: data.split('Series Crew')[0],
'Cinematography by</a>(.*?)</table>',
@ -53,7 +53,7 @@ class Imdb(SiteParser):
'type': 'list'
},
'directors': {
'page': 'fullcredits',
'page': 'combined',
're': [
lambda data: data.split('Series Crew')[0],
'Directed by</a>(.*?)</table>',
@ -62,7 +62,7 @@ class Imdb(SiteParser):
'type': 'list'
},
'editors': {
'page': 'fullcredits',
'page': 'combined',
're': [
lambda data: data.split('Series Crew')[0],
'Film Editing by</a>(.*?)</table>',
@ -152,7 +152,7 @@ class Imdb(SiteParser):
'type': 'string'
},
'writers': {
'page': 'fullcredits',
'page': 'combined',
're': [
lambda data: data.split('Series Crew')[0],
'Writing credits</a>(.*?)</table>',

View file

@ -1,10 +1,10 @@
# -*- coding: utf-8 -*-
# vi:si:et:sw=4:sts=4:ts=4
import re
from datetime import datetime
from ox.cache import readUrlUnicode
from ox import stripTags, decodeHtml
from ..cache import readUrlUnicode
from .. import stripTags, decodeHtml
from ..utils import datetime
def cleanup(key, data, data_type):