cleaning up impawards module

oxweb/impawards.py

@@ -9,88 +9,80 @@ from oxlib.text import findRe
 
 import imdb
 
+def getData(id):
+    '''
+    >>> getData('1991/silence_of_the_lambs')['imdbId']
+    u'0102926'
 
-def getMovieData(title = '', director = '', imdbId = ''):
+    >>> getData('1991/silence_of_the_lambs')['posters'][0]
-    data = {'posterUrls': []}
+    u'http://www.impawards.com/1991/posters/silence_of_the_lambs_ver1_xlg.jpg'
-    if not imdbId:
-        imdbId = imdb.getMovieId(title, director)
-    print imdbId
-    html = getUrlUnicode('http://impawards.com/archives/latest.html', timeout = 0)
-    pages = int(findRe(html, '<a href = page(.*?).html>'))
-    for page in range(pages + 1, 0, -1):
-        print page
-        if page <= pages:
-            html = getUrlUnicode('http://impawards.com/archives/page%s.html' % page, timeout = -1)
-        urls = parseArchivePage(html)
-        print urls
-        for url in urls:
-            html = getUrlUnicode(url)
-            d = parseMoviePage(html)
-            print d
-            if d['imdbId'] == imdbId:
-                data['posterUrls'].append(d['posterUrl'])
-                print d['posterUrl']
-    data['posterUrls'].sort()
-    return data
-            
-def parseArchivePage(html):
-    urls = []
-    results = re.compile('<a href = \.\./(.*?)>', re.DOTALL).findall(html)
-    for result in results:
-        urls.append('http://impawards.com/%s' % result)
-    return urls
 
-def parseMoviePage(html):
+    >>> getData('1991/silence_of_the_lambs')['url']
-    data = {}
+    u'http://www.impawards.com/1991/silence_of_the_lambs_ver1.html'
+    '''
+    data = {
+        'url': getUrl(id)
+    }
+    html = getUrlUnicode(data['url'])
     data['imdbId'] = findRe(html, 'imdb.com/title/tt(.*?) ')
     data['title'] = stripTags(findRe(html, '<p class="name white">(.*?) \(<a href="alpha1.html">'))
     data['year'] = findRe(html, '\(<a href="alpha1.html">(.*?)</a>\)')
-    result = findRe(html, '<a href = (\w*?_xlg.html)')
+    data['posters'] = []
-    if result:
+    results = re.compile('<a href = (%s.*?html)' % id[5:], re.DOTALL).findall(html)
-        url = 'http://impawards.com/%s/%s' % (data['year'], result)
+    for result in results:
-        html = getUrlUnicode(url, timeout = -1)
+        result = result.replace('_xlg.html', '.html')
-        data['posterUrl'] = 'http://impawards.com/%s/%s' % (data['year'], findRe(html, '<img SRC="(.*?)"'))
+        print result
-    else:
+        url = 'http://www.impawards.com/%s/%s' % (data['year'], result)
-        data['posterUrl'] = 'http://impawards.com/%s/%s' % (data['year'], findRe(html, '<img src="(posters.*?)" alt='))
+        html = getUrlUnicode(url)
+        result = findRe(html, '<a href = (\w*?_xlg.html)')
+        if result:
+            url = 'http://www.impawards.com/%s/%s' % (data['year'], result)
+            html = getUrlUnicode(url)
+            poster = 'http://www.impawards.com/%s/%s' % (data['year'], findRe(html, '<img SRC="(.*?)"'))
+        else:
+            poster = 'http://www.impawards.com/%s/%s' % (data['year'], findRe(html, '<img src="(posters.*?)" alt='))
+        data['posters'].append(poster)
     return data
 
-def archivePosters():
+def getId(url):
-    import os
+    split = url.split('/')
-    from oxlib.net import getUrl
+    year = split[3]
-    pathname = '/Volumes/Rolux Home/Desktop/Data/impawards.com'
+    split = split[4][:-5].split('_')
-    html = getUrlUnicode('http://impawards.com/archives/latest.html', timeout = 0)
+    if split[-1] == 'xlg':
+        split.pop()
+    if findRe(split[-1], 'ver\d+$'):
+        split.pop()
+    id = '%s/%s' % (year, '_'.join(split))
+    return id
+
+def getIds():
+    ids = []
+    html = getUrlUnicode('http://www.impawards.com/archives/latest.html', timeout = 0)
     pages = int(findRe(html, '<a href= page(.*?).html>'))
     for page in range(pages + 1, 0, -1):
-        print "Page %d of %d" % (page, pages)
+        for id in getIdsByPage(page):
-        if page <= pages:
+            if not id in ids:
-            html = getUrlUnicode('http://impawards.com/archives/page%s.html' % page, timeout = -1)
+                ids.append(id)
-        urls = parseArchivePage(html)
+    return ids
-        for url in urls:
-            html = getUrlUnicode(url)
-            data = parseMoviePage(html)
-            print data
-            if '"' in data['posterUrl']:
-                print url
-                sys.exit()
-            dirname = '%s/%s/%s/%s' % (pathname, data['imdbId'][:1], data['imdbId'][:4], data['imdbId'])
-            filename = '%s/%s' % (dirname, os.path.split(data['posterUrl'])[1])
-            if not os.path.exists(filename):
-                jpg = getUrl(data['posterUrl'])
-                if not os.path.exists(dirname):
-                    os.makedirs(dirname)
-                f = open(filename, 'w')
-                f.write(jpg)
-                f.close()
-    
-def cleanup():
-    for dirname, dirs, files in os.walk('/Volumes/Rolux Home/Desktop/Data/impawards.com'):
-        for filename in files:
-            if '"' in filename:
-                print filename
-                os.remove(dirname + '/' + filename)
 
+def getIdsByPage(page):
+    ids = []
+    html = getUrlUnicode('http://www.impawards.com/archives/page%s.html' % page, timeout = -1)
+    results = re.compile('<a href = \.\./(.*?)>', re.DOTALL).findall(html)
+    for result in results:
+        url = 'http://impawards.com/%s' % result
+        ids.append(getId(url))
+    return set(ids)
+
+def getUrl(id):
+    url = "http://www.impawards.com/%s.html" % id
+    html = getUrlUnicode(url)
+    if findRe(html, "No Movie Posters on This Page"):
+        url = "http://www.impawards.com/%s_ver1.html" % id
+    return url
 
 if __name__ == '__main__':
-    # cleanup()
+    print getData("1982/blade_runner")
-    archivePosters()
+    print getData("1991/silence_of_the_lambs")
-    getMovieData('Brick', 'Rian Johnson')
+    print getData("1999/matrix")
+    getIds()