edward/depicts
1
0
Fork 0
Code Issues 8 Pull requests Packages Projects Releases Wiki Activity

Bug fix 'Detroit Institute of Arts' parser.

Browse source
This commit is contained in:
Edward Betts 2019-10-09 22:03:51 +01:00
parent e38e1b994d
commit 04091988de
1 changed files with 7 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
depicts/dia.py
View file

@ -6,7 +6,10 @@ import re
re_url = re.compile(r'https?://www.dia.org/art/collection/object/(.+)$') re_url = re.compile(r'https?://www.dia.org/art/collection/object/(.+)$')
def get_html(url): def get_html(url):
catalog_id = re_url.search(url).group(1).replace('/', '_') m = re_url.search(url).group(1).replace('/', '_')
if not m:
return
catalog_id = m.group(1).replace('/', '_')
filename = f'cache/dia_{catalog_id}.html' filename = f'cache/dia_{catalog_id}.html'
@ -47,4 +50,6 @@ def parse_html(html):
} }
def get_catalog(url): def get_catalog(url):
return parse_html(get_html(url)) html = get_html(url)
if html:
return parse_html(html)