make sure tests work again, fix to32

ox/web/criterion.py

@@ -18,13 +18,13 @@ def getUrl(id):
 def getData(id):
     '''
     >>> getData('1333')['imdbId']
-    '0060304'
+    u'0060304'
 
     >>> getData('236')['posters'][0]
-    'http://criterion_production.s3.amazonaws.com/release_images/1586/ThirdManReplace.jpg'
+    u'http://criterion_production.s3.amazonaws.com/release_images/1586/ThirdManReplace.jpg'
 
     >>> getData('786')['posters'][0]
-    'http://criterion_production.s3.amazonaws.com/product_images/185/343_box_348x490.jpg'
+    u'http://criterion_production.s3.amazonaws.com/product_images/185/343_box_348x490.jpg'
     '''
     data = {
         "url": getUrl(id)
@@ -50,7 +50,7 @@ def getData(id):
         data["posters"] = [result]
     else:
         html_ = readUrlUnicode(result)
-        result = findRe(html_, "<a href=\"http://www.criterion.com/films/%s\">(.*?)</a>" % id)
+        result = findRe(html_, '<a href="http://www.criterion.com/films/%s.*?">(.*?)</a>' % id)
         result = findRe(result, "src=\"(.*?)\"")
         data["posters"] = [result.replace("_w100", "")]
     result = findRe(html, "<img alt=\"Film Still\" height=\"252\" src=\"(.*?)\"")
@@ -60,6 +60,7 @@ def getData(id):
     else:
         data["stills"] = [findRe(html, "\"thumbnailURL\", \"(.*?)\"")]
         data["trailers"] = [findRe(html, "\"videoURL\", \"(.*?)\"")]
+
     data['imdbId'] = imdb.getMovieId(data['title'], data['director'], data['year'])
     return data
 

ox/web/dailymotion.py

@@ -1,22 +1,22 @@
 # -*- coding: utf-8 -*-
-# vi:si:et:sw=4:sts=4:ts=4
-import re
-from urllib import unquote
-from ox.cache import readUrl
-
-
-def getVideoUrl(url):
-    '''
-    >>> getVideoUrl('http://www.dailymotion.com/relevance/search/priere%2Bpour%2Brefuznik/video/x3opar_priere-pour-refuznik-1-jeanluc-goda_shortfilms').split('?key')[0]
-    'http://www.dailymotion.com/get/16/320x240/flv/6191379.flv'
-
-    >>> getVideoUrl('http://www.dailymotion.com/relevance/search/priere%2Bpour%2Brefuznik/video/x3ou94_priere-pour-refuznik-2-jeanluc-goda_shortfilms').split('?key')[0]
-    'http://www.dailymotion.com/get/15/320x240/flv/6197800.flv'
-    '''
-    data = readUrl(url)
-    video = re.compile('''video", "(.*?)"''').findall(data)
-    for v in video:
-       v =  unquote(v).split('@@')[0]
-       return "http://www.dailymotion.com" + v
-    return ''
-
+# vi:si:et:sw=4:sts=4:ts=4
+import re
+from urllib import unquote
+from ox.cache import readUrl
+
+
+def getVideoUrl(url):
+    '''
+    >>> getVideoUrl('http://www.dailymotion.com/relevance/search/priere%2Bpour%2Brefuznik/video/x3opar_priere-pour-refuznik-1-jeanluc-goda_shortfilms').split('?auth')[0]
+    'http://www.dailymotion.com/cdn/FLV-320x240/video/x3opar_priere-pour-refuznik-1-jean-luc-god_shortfilms.flv'
+
+    >>> getVideoUrl('http://www.dailymotion.com/relevance/search/priere%2Bpour%2Brefuznik/video/x3ou94_priere-pour-refuznik-2-jeanluc-goda_shortfilms').split('?auth')[0]
+    'http://www.dailymotion.com/cdn/FLV-320x240/video/x3ou94_priere-pour-refuznik-2-jean-luc-god_shortfilms.flv'
+    '''
+    data = readUrl(url)
+    video = re.compile('''video", "(.*?)"''').findall(data)
+    for v in video:
+       v =  unquote(v).split('@@')[0]
+       return v
+    return ''
+

ox/web/imdb.py

@@ -249,14 +249,20 @@ class ImdbCombined(Imdb):
 def getMovieId(title, director='', year=''):
     '''
     >>> getMovieId('The Matrix')
-    '0133093'
+    u'0133093'
+
+    >>> getMovieId('2 or 3 Things I Know About Her', 'Jean-Luc Godard')
+    u'0060304'
+
+    >>> getMovieId('2 or 3 Things I Know About Her', 'Jean-Luc Godard', '1967')
+    u'0060304'
     '''
-    if year:
-        title = "%s (%s)" % (title, year)
     if director:
-        query = 'site:imdb.com %s "%s"' % (director, title)
+        query = 'site:imdb.com %s "%s" ' % (director, title)
     else:
-        query = 'site:imdb.com "%s"' % title
+        query = 'site:imdb.com "%s" ' % title
+    if year:
+        query += year
     for (name, url, desc) in google.find(query, 5, timeout=-1):
         if url.startswith('http://www.imdb.com/title/tt'):
             return url[28:35]

ox/web/impawards.py

@@ -14,7 +14,7 @@ def getData(id):
     u'0102926'
 
     >>> getData('1991/silence_of_the_lambs')['posters'][0]
-    u'http://www.impawards.com/1991/posters/silence_of_the_lambs_ver1_xlg.jpg'
+    u'http://www.impawards.com/1991/posters/silence_of_the_lambs_ver1.jpg'
 
     >>> getData('1991/silence_of_the_lambs')['url']
     u'http://www.impawards.com/1991/silence_of_the_lambs_ver1.html'
@@ -77,10 +77,10 @@ def getIdsByPage(page):
     return set(ids)
 
 def getUrl(id):
-    url = "http://www.impawards.com/%s.html" % id
+    url = u"http://www.impawards.com/%s.html" % id
     html = readUrlUnicode(url)
     if findRe(html, "No Movie Posters on This Page"):
-        url = "http://www.impawards.com/%s_ver1.html" % id
+        url = u"http://www.impawards.com/%s_ver1.html" % id
     return url
 
 if __name__ == '__main__':