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

more raw regexp strings

Browse source
This commit is contained in:
j 2024-08-30 13:30:47 +02:00
commit ae10c5c9b9
11 changed files with 45 additions and 45 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ox/web/google.py
View file

@ -60,7 +60,7 @@ def find(query, max_results=DEFAULT_MAX_RESULTS, timeout=DEFAULT_TIMEOUT):
url += '&start=%d' % offset
data = read_url(url, timeout=timeout)
data = re.sub('<span class="f">(.*?)</span>', '\\1', data)
for a in re.compile('<a href="(htt\S+?)".*?>(.*?)</a>.*?<span class="st">(.*?)<\/span>').findall(data):
for a in re.compile(r'<a href="(htt\S+?)".*?>(.*?)</a>.*?<span class="st">(.*?)<\/span>').findall(data):
results.append((strip_tags(decode_html(a[1])), a[0], strip_tags(decode_html(a[2]))))
if len(results) >= max_results:
break