import sys
import livewire
from csvutils import write_csv
# csvcut -c 3 livewire_events.csv | sort | uniq > livewire_venueid.txt
# cat livewire_venueid.txt | xargs python scrape_venues.py
if __name__ == '__main__':
venues = []
for venueid in sys.argv[1:]:
print venueid
venue = livewire.parse_venue(venueid)
if 'links' in venue:
venue['venuepage_label'] = venue['links'][0]['label']
venue['venuepage_href'] = venue['links'][0]['href']
else:
venue['venuepage_label'] = ''
venue['venuepage_href'] = ''
venues.append(venue)
write_csv('livewire_venues.csv',venues,'name','url','venuepage_label','venuepage_href','street-address','locality','region','phone','mail','postal-code','lat','lon')
def write_events(events):
write_csv('events.csv',events,'name','venue','venue_url','date')
import json
import csvutils
import codecs
import nolaflickr
if __name__ == '__main__':
f = codecs.open('artists.txt','r','utf-8')
all_authors = []
for l in f:
all_authors.append(l.strip())
data = json.load(open('artist_info.json','r'))
for a in data:
name = a['name']
a['summary'] = a.get('bio_summary','')
a['image'] = a.get('image_large','')
a['image_attrib'] = a.get('url','')
a['livewire_id'] = a.get('mbid','')
if name in all_authors:
all_authors.remove(name)
for name in all_authors:
author = dict(name=name)
flickr = nolaflickr.find_flickr_image(name)
if flickr:
author['image_attrib'] = flickr[0]
author['image'] = flickr[1]
data.append(author)
data.sort(key=lambda x:x['name'])
csvutils.write_csv('artists.csv',data,'name','tags','summary','url','livewire_id','image','image_attrib')
def write_events(events):
print events
write_csv('livewire_events.csv',events,'name','venue','venueid','venue_url','venueid','date')