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

fix google parser, and by that imdb id lookup, fixes #1545

Browse source
This commit is contained in:
j 2013-05-31 22:05:25 +02:00
parent cb3701d3e2
commit 8038b0d13f
1 changed files with 1 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
ox/web/google.py
View file

@ -31,9 +31,7 @@ def find(query, max_results=DEFAULT_MAX_RESULTS, timeout=DEFAULT_TIMEOUT):
data = read_url(url, timeout=timeout) data = read_url(url, timeout=timeout)
results = [] results = []
data = re.sub('<span class="f">(.*?)</span>', '\\1', data) data = re.sub('<span class="f">(.*?)</span>', '\\1', data)
for a in re.compile( for a in re.compile('<a href="(htt\S+?)".*?>(.*?)</a>.*?<span class="st">(.*?)<\/span>').findall(data):
'<a href="(\S+?)" class=l .*?>(.*?)</a>.*?<span class="st">(.*?)<\/span>'
).findall(data):
results.append((strip_tags(decode_html(a[1])), a[0], strip_tags(decode_html(a[2])))) results.append((strip_tags(decode_html(a[1])), a[0], strip_tags(decode_html(a[2]))))
if len(results) >= max_results: if len(results) >= max_results:
break break