X-Git-Url: https://git.mdrn.pl/redakcja.git/blobdiff_plain/19e20c4e4b6a7940977a293698d61e75810ff321..7319409f3463bce5b12e72a6ba18580ec9a9c029:/apps/cover/forms.py?ds=sidebyside diff --git a/apps/cover/forms.py b/apps/cover/forms.py index d726f1fa..e373a6cb 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) @@ -60,7 +63,7 @@ class FlickrForm(forms.Form): except AssertionError: raise forms.ValidationError('Error reading license name.') - m = re.search(r'By ([^<]*)', html) + m = re.search(r'([^<]*)', html) if m: self.cleaned_data['author'] = "%s@Flickr" % m.group(1) else: @@ -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*