From 2d649c8fe8dd70c00c70b83d2f139f6a3fe1d0aa Mon Sep 17 00:00:00 2001 From: =?utf8?q?Aleksander=20=C5=81ukasz?= Date: Tue, 30 Apr 2013 09:58:03 +0200 Subject: [PATCH] Fixes #2688 --- apps/cover/forms.py | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/apps/cover/forms.py b/apps/cover/forms.py index d726f1fa..7fc6a33e 100755 --- a/apps/cover/forms.py +++ b/apps/cover/forms.py @@ -37,6 +37,9 @@ class FlickrForm(forms.Form): source_url = forms.URLField(label=_('Flickr URL')) def clean_source_url(self): + def normalize_html(html): + return re.sub('[\t\n]', '', html) + url = self.cleaned_data['source_url'] m = re.match(r'(https?://)?(www\.|secure\.)?flickr\.com/photos/(?P[^/]+)/(?P\d+)/?', url) if not m: @@ -45,7 +48,7 @@ class FlickrForm(forms.Form): base_url = "https://www.flickr.com/photos/%s/%s/" % (author_slug, img_id) try: - html = urlopen(url).read().decode('utf-8') + html = normalize_html(urlopen(url).read().decode('utf-8')) except: raise forms.ValidationError('Error reading page.') match = re.search(r'Some rights reserved', html) @@ -72,7 +75,7 @@ class FlickrForm(forms.Form): self.cleaned_data['title'] = m.group(1) url_size = base_url + "sizes/o/" - html = urlopen(url_size).read().decode('utf-8') + html = normalize_html(urlopen(url_size).read().decode('utf-8')) m = re.search(r'
\s*