0x2620/python-ox
2
1
Fork 0
Code Issues Pull requests Releases Wiki Activity

criterion.py: fix title and synopsis detection

Browse source
This commit is contained in:
rolux 2013-05-31 11:03:09 +02:00
parent 4f0654db68
commit 647f027e8a
1 changed files with 3 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
ox/web/criterion.py
View file

@ -35,14 +35,14 @@ def get_data(id, timeout=ox.cache.cache_timeout, get_imdb=False):
html = ox.cache.read_url(data["url"], timeout=timeout) html = ox.cache.read_url(data["url"], timeout=timeout)
data["number"] = find_re(html, "<li>Spine #(\d+)") data["number"] = find_re(html, "<li>Spine #(\d+)")
data["title"] = find_re(html, "<meta property=['\"]og:title['\"] content=['\"](.*?)['\"]") data["title"] = find_re(html, "<h1 class=\"movietitle\">(.*?)</h1>")
data["title"] = data["title"].split(u' \u2014 The Television Version')[0] data["title"] = data["title"].split(u' \u2014 The Television Version')[0]
data["director"] = strip_tags(find_re(html, "<h2 class=\"director\">(.*?)</h2>")) data["director"] = strip_tags(find_re(html, "<h2 class=\"director\">(.*?)</h2>"))
results = find_re(html, '<div class="left_column">(.*?)</div>') results = find_re(html, '<div class="left_column">(.*?)</div>')
results = re.compile("<li>(.*?)</li>").findall(results) results = re.compile("<li>(.*?)</li>").findall(results)
data["country"] = results[0] data["country"] = results[0]
data["year"] = results[1] data["year"] = results[1]
data["synopsis"] = strip_tags(find_re(html, "<p><strong>SYNOPSIS:</strong> (.*?)</p>")) data["synopsis"] = strip_tags(find_re(html, "<div class=\"content_block last\">.*?<p>(.*?)</p>"))
result = find_re(html, "<div class=\"purchase\">(.*?)</div>") result = find_re(html, "<div class=\"purchase\">(.*?)</div>")
if 'Blu-Ray' in result or 'Essential Art House DVD' in result: if 'Blu-Ray' in result or 'Essential Art House DVD' in result:
@ -72,8 +72,7 @@ def get_data(id, timeout=ox.cache.cache_timeout, get_imdb=False):
if timeout == ox.cache.cache_timeout: if timeout == ox.cache.cache_timeout:
timeout = -1 timeout = -1
if get_imdb: if get_imdb:
data['imdbId'] = imdb.get_movie_id(data['title'], data['imdbId'] = imdb.get_movie_id(data['title'], data['director'], data['year'], timeout=timeout)
data['director'], data['year'], timeout=timeout)
return data return data
def get_ids(page=None): def get_ids(page=None):