98 lines
3.1 KiB
Python
98 lines
3.1 KiB
Python
import os, sys
|
||
from datetime import datetime
|
||
from dateutil import relativedelta
|
||
|
||
sys.path.append('/var/www/digisnaxx.ado/scrapers')
|
||
import dtss
|
||
dtss.getReady()
|
||
|
||
from time import sleep
|
||
from pprint import pprint as ppr
|
||
import pytz
|
||
|
||
from events.models import Organization, Scraper
|
||
|
||
import events.digitools as digitools
|
||
|
||
venue, created = Organization.objects.get_or_create(
|
||
name="St Paul Chamber Orchestra",
|
||
city="St Paul",
|
||
website="https://thespco.org",
|
||
is_venue = False
|
||
)
|
||
|
||
scraper,item_count_start, virtcal = digitools.getScraper(venue, venue.website, 'msp')
|
||
|
||
# Time Signatures
|
||
tz = pytz.timezone("US/Central")
|
||
DATETIME_FORMAT = '%A, %B %d, %Y – %I:%M %p'
|
||
|
||
def get_events(ps, event_type):
|
||
contents = ps.xpath('.//*/div[@class="event-title"]/a/@href')
|
||
for c in set(contents):
|
||
try:
|
||
link = 'https://content.thespco.org' + c
|
||
ps = digitools.getSource(br, link)
|
||
ntitle = ps.xpath('.//*/article/h1/text()')
|
||
subtitle = ps.xpath('.//*/article/h1/em/text()')
|
||
event = {}
|
||
event['scraper'] = scraper
|
||
event['calendars'] = [scraper.calendar]
|
||
if len(subtitle) == 1:
|
||
if len(ntitle) == 2:
|
||
title = ntitle[0] + subtitle[0] + ntitle[1]
|
||
elif ntitle[0].startswith(" "):
|
||
title = subtitle[0] + ntitle[0]
|
||
else:
|
||
title = ntitle[0] + subtitle[0]
|
||
else:
|
||
title = ntitle[0]
|
||
|
||
events = ps.xpath('.//*/div[@class="day"]')
|
||
for e in events:
|
||
new_venue = e.xpath('.//*/strong[@class="venue"]/text()')[0].strip()
|
||
location = e.xpath('.//*/span[@class="location"]/text()')[0].strip()
|
||
if 'Minneapolis' in location:
|
||
location = 'Minneapolis'
|
||
elif 'St. Paul' in location:
|
||
location = 'St. Paul'
|
||
else:
|
||
location = location
|
||
|
||
venue, created = Organization.objects.get_or_create(
|
||
name=new_venue,
|
||
city=location,
|
||
is_venue = True
|
||
)
|
||
|
||
dateTime = e.xpath('.//*/h3[@class="date"]/text()')[0].replace("\n", "").replace("\t", "").strip()
|
||
event['dateStamp'] = datetime.strptime(dateTime, DATETIME_FORMAT)
|
||
event['venue'] = venue
|
||
event['location'] = location
|
||
event['title'] = "SPCO: " + title
|
||
event['link'] = link
|
||
event_type = "Mu"
|
||
digitools.createBasicEvent(event, event_type, venue)
|
||
scraper.items+=1
|
||
except Exception as e:
|
||
print("ERROR: ", e)
|
||
print("\n\n+++\n\n")
|
||
|
||
if len(sys.argv) >= 2:
|
||
arg1 = sys.argv[1]
|
||
br = digitools.getBrowser(arg1)
|
||
else:
|
||
print("No run_env")
|
||
quit()
|
||
|
||
# Get Event Page Link(s)
|
||
links = digitools.createURLNoZero("https://content.thespco.org/events/calendar/")
|
||
|
||
for link in links:
|
||
ps = digitools.getSource(br, link)
|
||
get_events(ps, "Mu")
|
||
sleep(3)
|
||
|
||
br.close()
|
||
digitools.updateScraper(scraper, item_count_start)
|