def test_get_urls(self):
text = """
Some junk
http://airmozilla/manage/events/1068/ stuff
https://etherpad.mozilla.org/sumo-mobile
"""
urls = list(scraper.get_urls(text))
eq_(
urls,
[
'http://airmozilla/manage/events/1068/',
'https://etherpad.mozilla.org/sumo-mobile'
]
)
def handle(self, *args, **options):
if not args:
raise CommandError(self.args)
for arg in args:
if arg.isdigit():
event = Event.objects.get(pk=arg)
else:
if '://' in arg:
slug = urlparse(arg).path.split('/')[1]
else:
slug = arg
event = Event.objects.get(slug=slug)
print scrape_urls(get_urls(event.additional_links))['text']
def event_transcript(request, id):
event = get_object_or_404(Event, id=id)
context = {}
from airmozilla.manage.scraper import get_urls, scrape_urls
scrapeable_urls = list(get_urls(event.additional_links))
if request.method == 'POST':
form = forms.EventTranscriptForm(
instance=event,
data=request.POST,
)
if form.is_valid():
form.save()
messages.success(
request,
'Event transcript saved.'
)
return redirect('manage:event_edit', event.pk)
else:
initial = {}
if request.GET.getlist('urls'):
response = scrape_urls(request.GET.getlist('urls'))
if response['text']:
initial['transcript'] = response['text']
errors = []
for result in response['results']:
if not result['worked']:
errors.append('%s: %s' % (result['url'], result['status']))
if errors:
errors.insert(0, 'Some things could not be scraped correctly')
messages.error(
request,
'\n'.join(errors)
)
form = forms.EventTranscriptForm(instance=event, initial=initial)
amara_videos = AmaraVideo.objects.filter(event=event)
context['event'] = event
context['amara_videos'] = amara_videos
context['form'] = form
context['scrapeable_urls'] = scrapeable_urls
return render(request, 'manage/event_transcript.html', context)
def test_get_urls(self):
text = """
Some junk
http://airmozilla/manage/events/1068/ stuff
https://etherpad.mozilla.org/sumo-mobile
hello, this is madness
https://docs.python.org/2/library/urlparse.html..
madness I say https://github.com/mozilla/airmozilla........
yes http://blog.mozilla.org/devtools/.
"""
urls = list(scraper.get_urls(text))
eq_(urls, [
'http://airmozilla/manage/events/1068/',
'https://etherpad.mozilla.org/sumo-mobile',
'https://docs.python.org/2/library/urlparse.html',
'https://github.com/mozilla/airmozilla',
'http://blog.mozilla.org/devtools/'
])
def test_get_urls(self):
text = """
Some junk
http://airmozilla/manage/events/1068/ stuff
https://etherpad.mozilla.org/sumo-mobile
hello, this is madness
https://docs.python.org/2/library/urlparse.html..
madness I say https://github.com/mozilla/airmozilla........
yes http://blog.mozilla.org/devtools/.
"""
urls = list(scraper.get_urls(text))
eq_(
urls,
[
'http://airmozilla/manage/events/1068/',
'https://etherpad.mozilla.org/sumo-mobile',
'https://docs.python.org/2/library/urlparse.html',
'https://github.com/mozilla/airmozilla',
'http://blog.mozilla.org/devtools/'
]
)
