import feedparser
import logging
import lxml.html
from datetime import datetime
import re
from lxml.html.clean import Cleaner
from fancyashow.extensions import ExtensionLibrary, ShowParser
from fancyashow.extensions.models import Venue, Performer, Show
from fancyashow.util import parsing as html_util
from fancyashow.util import dates as date_util
from fancyashow.util import lang as lang_util
extensions = ExtensionLibrary()
class Glasslands(ShowParser):
BASE_URL = "http://www.glasslands.com/"
FEED_URL = "http://glasslands.blogspot.com/feeds/posts/default"
SHOW_DIVIDER_RE = re.compile('___+')
HEADER_SEP_RE = re.compile('(?:(?:>)|/){2}')
BODY_SKIP = [
re.compile('rsvp', re.I),
re.compile('tickets', re.I)
]
REPLACEMENTS = [
(re.compile('<\s*br\s*/?\s*>', re.I), '\n'),
(re.compile('<\s*div\s*.*?>', re.I), ''),
(re.compile('<\s*/\s*div\s*>', re.I), '\n'),
(re.compile('details\s+tba', re.I), '')
]
def __init__(self, *args, **kwargs):
import logging
import re
from fancyashow.extensions import ExtensionLibrary, ShowParser
from fancyashow.extensions.models import Venue, Performer, Show
from fancyashow.util import parsing as html_util
from fancyashow.util import dates as date_util
from fancyashow.util import lang as lang_util
extensions = ExtensionLibrary()
class KnittingFactory(ShowParser):
BASE_URL = "http://bk.knittingfactory.com/"
CALENDAR_URL = "http://bk.knittingfactory.com/calendar/"
IS_EVENT = re.compile("http://bk.knittingfactory.com/event-details/\?tfly_event_id=\d+")
def __init__(self, *args, **kwargs):
super(KnittingFactory, self).__init__(*args, **kwargs)
self._parser = None
def next(self):
if not self._parser:
self._parser = self._get_parser()
while(True):
return self._parser.next()
raise StopIteration
def _get_parser(self):
show_urls = html_util.get_show_urls(self.CALENDAR_URL, ".tfly-calendar", 'td', self.IS_EVENT)
# coding=UTF-8
import logging
import re
from fancyashow.extensions import ExtensionLibrary, ShowParser
from fancyashow.extensions.models import Venue, Performer, Show
from fancyashow.util import parsing as html_util
from fancyashow.util import dates as date_util
from fancyashow.util import lang as lang_util
logger = logging.getLogger(__name__)
extensions = ExtensionLibrary()
class Pianos(ShowParser):
BASE_URL = "http://www.pianosnyc.com/"
CALENDAR_URLS = ['http://www.pianosnyc.com/showroom', 'http://www.pianosnyc.com/upstairs']
IS_EVENT = re.compile("http://www.pianosnyc.com/(upstairs|showroom)/[^/]+-\d+")
DATE_RE = re.compile('(\w+,\s+\w+\s+\d+,\s+\d+)')
def __init__(self, *args, **kwargs):
super(Pianos, self).__init__(*args, **kwargs)
self._parser = None
def next(self):
if not self._parser:
self._parser = self._get_parser()
while(True):
return self._parser.next()
import logging
from datetime import datetime
from fancyashow.extensions import ExtensionLibrary, ResourceExtractor, ShowResourceHandler
from fancyashow.extensions import ArtistResourceHandler, ArtistMediaExtractor
from fancyashow.extensions.models import VideoInfo
from fancyashow.util.resources import URLMatch, HrefMatcher, ParamMatcher
from fancyashow.util import lang, artist_matcher
from fancyashow.systems.vimeo import api
logger = logging.getLogger(__name__)
extensions = ExtensionLibrary()
HREF_URL = URLMatch('(www\.)?vimeo.com/(?P<video_id>\d+)\/?')
EMBED_URL = URLMatch('(www\.)?vimeo.com/.*?clip_id=(?P<video_id>\d+)')
class VimeoResourceExtractor(ResourceExtractor):
def resources(self, node):
def url(m):
return 'vimeo-video:%s' % m.group('video_id')
ret = []
ret.extend([url(m) for m in HrefMatcher( node, HREF_URL)])
ret.extend([url(m) for m in ParamMatcher(node, 'movie', EMBED_URL)])
return ret
def _trans_video(video, source_id):
import re
import logging
from datetime import datetime, timedelta
from fancyashow.extensions import ExtensionLibrary, ShowParser
from fancyashow.extensions.models import Venue, Performer, Show
from fancyashow.util import parsing as html_util
from fancyashow.util import dates as date_util
from fancyashow.util import lang as lang_util
extensions = ExtensionLibrary()
logger = logging.getLogger(__name__)
class BellHouse(ShowParser):
BASE_URL = "http://www.thebellhouseny.com/"
CALENDAR_URL = "http://www.thebellhouseny.com/calendar.php"
DATE_RE = re.compile("\w+ (?P<month>\d+)/(?P<day>\d+)")
TIME_RE = re.compile('\s+(?P<time>\d+(?:\s*:\s*\d+)?\s*(?:am|pm|a\.m\.|p\.\m))\s*', re.IGNORECASE)
def __init__(self, *args, **kwargs):
super(BellHouse, self).__init__(*args, **kwargs)
self._parser = None
def next(self):
if not self._parser:
self._parser_started = datetime.now()
self._parser = self._get_parser()
while(True):
return self._parser.next()
import logging
import lxml.html
import re
from lxml.html.clean import Cleaner
from datetime import datetime
from fancyashow.extensions import ExtensionLibrary, ShowParser
from fancyashow.extensions.models import Venue, Performer, Show
from fancyashow.util import parsing as html_util
from fancyashow.util import dates as date_util
from fancyashow.util import lang as lang_util
logger = logging.getLogger(__name__)
extensions = ExtensionLibrary()
class BruarFalls(ShowParser):
BASE_URL = "http://www.bruarfalls.com/"
NUM_RE = re.compile('^\s*\d+\s*(?:st|nd|rd|th):\s*', re.IGNORECASE | re.MULTILINE)
def __init__(self, *args, **kwargs):
super(BruarFalls, self).__init__(*args, **kwargs)
self._parser = None
def next(self):
if not self._parser:
self._parse_started = datetime.now()
self._parser = self._get_parser()
while(True):
return self._parser.next()
from fancyashow.extensions import ExtensionLibrary
from fancyashow.parsers.common.lastfm import LastFMParser
from fancyashow.extensions.models import Venue
extensions = ExtensionLibrary()
class IrvingPlaza(LastFMParser):
def venue_id(self):
return 8778815
def venue(self):
return Venue('Irving Plaza', 'http://www.irvingplaza.com/')
@classmethod
def id(self):
return 'us.ny.manhattan.irving-plaza'
extensions.register_show_parser(IrvingPlaza)
import logging
from copy import deepcopy
from datetime import datetime, timedelta
from fancyashow.extensions import ExtensionLibrary
from fancyashow.extensions.artists import ArtistProcessor
from fancyashow.processing import ProcessorSetup
from fancyashow.db.models import SystemStat
logger = logging.getLogger(__name__)
extensions = ExtensionLibrary()
class ArtistRanking(ArtistProcessor):
def __init__(self, library, settings):
super(ArtistRanking, self).__init__(library, settings)
self.sample_days = self.get_required_setting(settings, 'sample_days')
self._stats = None
self.sample_end = datetime.today() + timedelta(days = 1)
self.sample_start = (datetime.today() - timedelta(days = self.sample_days)).replace(hour = 0, minute = 0, second = 0)
def stats(self):
if not self._stats:
stats = { }
for stat in SystemStat.objects():
stats[ stat.system_id ] = stat
self._stats = stats
return self._stats
import logging
from datetime import datetime
import urlparse
import re
from fancyashow.extensions import ExtensionLibrary, ShowParser
from fancyashow.extensions.models import Venue, Performer, Show
from fancyashow.util import parsing as html_util
from fancyashow.util import dates as date_util
from fancyashow.util import lang as lang_util
extensions = ExtensionLibrary()
class Coco66(ShowParser):
BASE_URL = "http://www.coco66.com/"
MONTH_FORMAT = 'http://coco66.com/?page=calendar&month=%(month)s&year=%(year)s'
IS_EVENT = re.compile("http://(?:www.)?coco66.com/\?page=event&id=\d+")
EVENT_ID = re.compile('id=(\d+)')
# Allows for 2009-09-01, Monday, October 11th, 2010, or Tonight
HEADER_PARSE = re.compile('(?P<date>(?:\d+-\d+-\d+)|(?:\w+\s+\d+/\d+)|(\w+,\s+\w+\s+\d+\w+,\s+\d+)|(?:tonight))\s*-\s*(?P<title>.*)', re.I)
MONTHS_AHEAD = 3
def __init__(self, *args, **kwargs):
super(Coco66, self).__init__(*args, **kwargs)
self._current_parser = None
self._date_queue = self._request_dates()
self._parsed_dates = { }
def _next_parser(self):
if self._date_queue:
return self._month_parser(self._date_queue.pop(0))
import logging
import urlparse
import re
from datetime import datetime
from fancyashow.extensions import ExtensionLibrary, ShowParser
from fancyashow.extensions.models import Venue, Performer, Show
from fancyashow.util import parsing as html_util
from fancyashow.util import dates as date_util
from fancyashow.util import lang as lang_util
extensions = ExtensionLibrary()
class LPR(ShowParser):
BASE_URL = "http://lepoissonrouge.com/"
CALENDAR_URL = "http://lepoissonrouge.com/calendar/%(year)s/%(month)s/"
IS_EVENT_URL_RE = re.compile('http://lepoissonrouge.com/events/view/\d+')
IS_ARTIST_URL_RE = re.compile('http://lepoissonrouge.com/events/artist/\d+')
MONTHS_AHEAD = 3
def __init__(self, *args, **kwargs):
super(LPR, self).__init__(*args, **kwargs)
self._current_parser = None
self._date_queue = self._request_dates()
def _next_parser(self):
if self._date_queue:
return self._month_parser(self._date_queue.pop(0))
return None
import logging
import re
import urllib2
import lxml.html
from lxml import etree
from fancyashow.extensions import ExtensionLibrary, ResourceExtractor, ShowResourceHandler, ArtistResourceHandler
from fancyashow.util.resources import URLMatch, HrefMatcher, TextMatcher
from fancyashow.db.models import ArtistProfile
from fancyashow.util import artist_matcher, parsing
logger = logging.getLogger(__name__)
extensions = ExtensionLibrary()
PROFILE_ID = "(?P<profile_id>[\d\w_.-]+)"
NAME_RE = re.compile('\s*(.+)(?:\s+\(.+?\)\s+on twitter.*)', re.I | re.M)
TWITTER_URL = URLMatch('(?:www\.)?twitter\.com/%s' % PROFILE_ID)
class TwitterResourceExtractor(ResourceExtractor):
def resources(self, node):
def uri(match):
return 'twitter-profile:%s' % m.group('profile_id')
ret = []
ret.extend( [ uri(m) for m in HrefMatcher(node, TWITTER_URL) ] )
ret.extend( [ uri(m) for m in TextMatcher(node, TWITTER_URL) ] )
return ret
import logging
from datetime import datetime
from fancyashow.extensions import ExtensionLibrary, ArtistMediaExtractor, ResourceExtractor
from fancyashow.extensions import ShowResourceHandler, ArtistResourceHandler
from fancyashow.extensions.models import VideoInfo
from fancyashow.db.models import ArtistProfile
from fancyashow.util.resources import URLMatch, HrefMatcher, ParamMatcher, TextMatcher
from fancyashow.util import artist_matcher
from bandcamp import BandCampService
from fancyashow.systems.bandcamp.settings import API_KEY
logger = logging.getLogger(__name__)
extensions = ExtensionLibrary()
PROFILE_ID = "(?P<profile_id>[\d\w_.-]+)"
HREF_URL = URLMatch('%s.bandcamp.com' % PROFILE_ID)
SYSTEM_ID = 'bandcamp'
class BandCampResourceExtractor(ResourceExtractor):
def resources(self, node):
def url(m):
return 'bandcamp-profile:%s' % m.group('profile_id')
ret = []
ret.extend([url(m) for m in HrefMatcher( node, HREF_URL)])
ret.extend([url(m) for m in TextMatcher( node, HREF_URL)])
import logging
from datetime import datetime
from fancyashow.extensions import ArtistProcessor, ResourceExtractorManager
from fancyashow.extensions import ExtensionLibrary
logger = logging.getLogger(__name__)
extensions = ExtensionLibrary()
# State form
# $system_id:$profile_id -> {
# last_parsed: $timestamp,
# resources: []
# }
class ProfileParser(ArtistProcessor):
def __init__(self, library, settings):
super(ProfileParser, self).__init__(library, settings)
self.update_interval = self.get_required_setting(settings, "update_interval")
self.resource_extractor = ResourceExtractorManager(library.resource_extractors())
@classmethod
def default_state(self):
return {}
def process(self, artist, state, dependent_states):
new_state = self.clone_state(state)
media = []
import logging
from datetime import date
from fancyashow.parsers.common.google_calendar import GoogleCalendarParser
from fancyashow.extensions import ExtensionLibrary, ShowParser
from fancyashow.extensions.models import Venue, Performer, Show
from fancyashow.util import parsing as html_util
from fancyashow.util import dates as date_util
from fancyashow.util import lang as lang_util
extensions = ExtensionLibrary()
logger = logging.getLogger(__name__)
class SpikeHill(GoogleCalendarParser):
def _process_recurring_entries(self, entries):
return []
def _process_entry_group(self, start_date, entries):
show = Show()
show.venue = self.venue()
show.performers = []
entries.sort(key = lambda e: e.when[0].start_time, reverse = True)
for entry in entries:
logger.debug("Processing entry: %s, starting on: %s" % (entry.title.text, entry.when[0].start_time))
# Full day events usually denote a title which we currently will simply skip
if 'T' not in entry.when[0].start_time:
logger.debug('Entry "%s" is an all day event, skipping' % entry.title.text)
import logging
import urlparse
import re
from fancyashow.extensions import ExtensionLibrary, ShowParser
from fancyashow.extensions.models import Venue, Performer, Show
from fancyashow.util import parsing as html_util
from fancyashow.util import dates as date_util
from fancyashow.util import lang as lang_util
extensions = ExtensionLibrary()
class BoweryPresentsBase(ShowParser):
BASE_URL = "http://www.brooklynbowl.com/"
CALENDAR_URL = "http://www.brooklynbowl.com/upcoming-events/"
IMAGE_RE = re.compile('background-image:\s*url\((?P<image_path>.+)\)')
def __init__(self, *args, **kwargs):
super(BoweryPresentsBase, self).__init__(*args, **kwargs)
self._parser = None
def next(self):
if not self._parser:
self._parser = self._get_parser()
while(True):
return self._parser.next()
raise StopIteration
import logging
from datetime import datetime
from fancyashow.extensions import ExtensionLibrary, ArtistMediaExtractor, ResourceExtractor
from fancyashow.extensions import ShowResourceHandler, ArtistResourceHandler
from fancyashow.extensions.models import VideoInfo
from fancyashow.util.resources import URLMatch, HrefMatcher, ParamMatcher, TagAttrMatcher
from fancyashow.util import artist_matcher
from fancyashow.systems.youtube import api
logger = logging.getLogger(__name__)
extensions = ExtensionLibrary()
HREF_URL = URLMatch('(www\.)?youtube.com/watch?(.+&)?v=(?P<video_id>[^&])+')
EMBED_URL = URLMatch('(www\.)?youtube.com/v/(?P<video_id>[^&]+)')
NEW_EMBED_URL = URLMatch('(www\.)?youtube.com/embed/(?P<video_id>[^&]+)')
class YouTubeResourceExtractor(ResourceExtractor):
def resources(self, node):
def url(m):
return 'youtube-video:%s' % m.group('video_id')
ret = []
ret.extend([url(m) for m in HrefMatcher( node, HREF_URL)])
ret.extend([url(m) for m in ParamMatcher(node, 'movie', EMBED_URL)])
ret.extend([url(m) for m in TagAttrMatcher(node, ['iframe'], ['src'], NEW_EMBED_URL)])
return ret
from datetime import datetime
from fancyashow.extensions import ExtensionLibrary, ShowParser
from fancyashow.extensions.models import Venue, Performer, Show
from fancyashow.util import parsing as html_util
from fancyashow.util import dates as date_util
from fancyashow.util import lang as lang_util
extensions = ExtensionLibrary()
class UnionPool(ShowParser):
BASE_URL = "http://unionpool.blogspot.com/"
def __init__(self, *args, **kwargs):
super(UnionPool, self).__init__(*args, **kwargs)
self._parser = None
def next(self):
if not self._parser:
self._parse_started = datetime.now()
self._parser = self._get_parser()
while(True):
return self._parser.next()
raise StopIteration
def _get_parser(self):
doc = html_util.fetch_and_parse(self.BASE_URL)
sidebar = doc.get_element_by_id("sidebar-right-1")
import logging
import urllib2
import lxml.html
import re
from datetime import datetime
from fancyashow.extensions import ExtensionLibrary, ShowParser
from fancyashow.extensions.models import Venue, Performer, Show
from fancyashow.util import parsing as html_util
from fancyashow.util import dates as date_util
from fancyashow.util import lang as lang_util
extensions = ExtensionLibrary()
class Europa(ShowParser):
BASE_URL = "http://www.europalive.net/"
CALENDAR_URL = "http://www.europalive.net/calendar.html"
IMAGE_RE = re.compile('/images/band_images/')
def __init__(self, *args, **kwargs):
super(Europa, self).__init__(*args, **kwargs)
self._parser = None
def next(self):
if not self._parser:
self._parse_started = datetime.now()
self._parser = self._get_parser()
while(True):
return self._parser.next()
from fancyashow.extensions import ExtensionLibrary
from fancyashow.parsers.common.lastfm import LastFMParser
from fancyashow.extensions.models import Venue
extensions = ExtensionLibrary()
class RadioCityMusicHall(LastFMParser):
def venue_id(self):
return 8906841
def venue(self):
return Venue('Radio City Music Hall', 'http://www.radiocity.com/')
@classmethod
def id(self):
return 'us.ny.manhattan.radio-city-music-hall'
extensions.register_show_parser(RadioCityMusicHall)
import re
from datetime import datetime
from fancyashow.extensions import ExtensionLibrary, ShowParser
from fancyashow.extensions.models import Venue, Performer, Show
from fancyashow.util import parsing as html_util
from fancyashow.util import dates as date_util
from fancyashow.util import lang as lang_util
extensions = ExtensionLibrary()
class Southpaw(ShowParser):
BASE_URL = "http://spsounds.com/"
CALENDAR_URL = "http://spsounds.com/calendar/"
IS_EVENT = re.compile("http://www.santospartyhouse.com/index/event/id/\d+")
def __init__(self, *args, **kwargs):
super(Southpaw, self).__init__(*args, **kwargs)
self._parser = None
def next(self):
if not self._parser:
self._parse_started = datetime.now()
self._parser = self._get_parser()
while(True):
return self._parser.next()
raise StopIteration
def _get_parser(self):
import logging
from datetime import datetime
from fancyashow.extensions import ExtensionLibrary, ArtistMediaExtractor, ResourceExtractor
from fancyashow.extensions import ShowResourceHandler, ArtistResourceHandler
from fancyashow.extensions.models import VideoInfo
from fancyashow.util.resources import URLMatch, HrefMatcher, ParamMatcher, TextMatcher
from fancyashow.util import artist_matcher
logger = logging.getLogger(__name__)
extensions = ExtensionLibrary()
PROFILE_ID = "(?P<profile_id>[\d\w_.-]+)"
HREF_URL = URLMatch('(www\.)?soundcloud.com/%s' % PROFILE_ID)
EMBED_URL = URLMatch('player.soundcloud.com/player.swf?url=http[s]?%3A%2F%2Fsoundcloud.com%2F(?P<profile_id>[^%]+)')
class SoundCloudResourceExtractor(ResourceExtractor):
def resources(self, node):
def url(m):
return 'soundcloud-profile:%s' % m.group('profile_id')
ret = []
ret.extend([url(m) for m in HrefMatcher( node, HREF_URL)])
ret.extend([url(m) for m in ParamMatcher(node, 'movie', EMBED_URL)])
ret.extend([url(m) for m in TextMatcher( node, HREF_URL)])
return ret
from fancyashow.extensions import ExtensionLibrary
from fancyashow.parsers.common.lastfm import LastFMParser
from fancyashow.extensions.models import Venue
extensions = ExtensionLibrary()
class RoselandBallroom(LastFMParser):
def venue_id(self):
return 8780835
def venue(self):
return Venue('Roseland Ballroom', 'http://www.roselandballroom.com/')
@classmethod
def id(self):
return 'us.ny.manhattan.roseland-ballroom'
extensions.register_show_parser(RoselandBallroom)
from datetime import datetime
from copy import deepcopy
import logging
from fancyashow.extensions import ExtensionLibrary
from fancyashow.extensions.shows import ShowProcessor
from fancyashow.processing import ProcessorSetup
from fancyashow.util import artist_matcher
logger = logging.getLogger(__name__)
extensions = ExtensionLibrary()
class ArtistAssociation(ShowProcessor):
def process(self, show, state, dependent_states):
artist_ids = []
for artist_info in show.artists:
if not artist_info.artist_id:
artist = artist_matcher.get_artist(artist_info.name)
if artist:
artist_info.artist_id = artist.id
if artist_info.artist_id:
artist_ids.append(artist_info.artist_id)
show.artist_ids = artist_ids
def cleanup(self, show, state):
pass
# encoding=UTF-8
import logging
from fancyashow.extensions import ExtensionLibrary, ShowParser
from fancyashow.extensions.models import Venue, Performer, Show
from fancyashow.parsers.common.lastfm import LastFMParser
from fancyashow.util import parsing as html_util
from fancyashow.util import dates as date_util
from fancyashow.util import lang as lang_util
import re
logger = logging.getLogger(__name__)
extensions = ExtensionLibrary()
class WebsterHall(LastFMParser):
def venue_id(self):
return 8778811
def venue(self):
return Venue('Webster Hall', "http://www.websterhall.com/")
@classmethod
def id(cls):
return 'us.ny.manhattan.webster-hall'
class WebsterHallStudio(LastFMParser):
def venue_id(self):
return 9004895
def venue(self):
from fancyashow.extensions import ExtensionLibrary
from fancyashow.parsers.common.myspace import MyspaceParser
from fancyashow.extensions.models import Venue
extensions = ExtensionLibrary()
class CameoGallery(MyspaceParser):
def venue(self):
return Venue('Cameo Gallery', 'http://www.myspace.com/cameogallery/')
@classmethod
def profile_id(self):
return 459194474
@classmethod
def id(self):
return 'us.ny.brooklyn.cameo-gallery'
extensions.register_show_parser(CameoGallery)
import logging
import re
from datetime import date
from fancyashow.parsers.common.google_calendar import GoogleCalendarParser
from fancyashow.extensions import ExtensionLibrary, ShowParser
from fancyashow.extensions.models import Venue, Performer, Show
from fancyashow.util import parsing as html_util
from fancyashow.util import dates as date_util
from fancyashow.util import lang as lang_util
extensions = ExtensionLibrary()
logger = logging.getLogger(__name__)
class Gutter(GoogleCalendarParser):
BACK_ROOM_RE = re.compile('^back\s+room\s*:?\s*', re.I)
def _process_recurring_entries(self, entries):
return []
def _process_entry(self, entry):
logger.debug("Processing entry: %s, starting on: %s" % (entry.title.text, entry.when[0].start_time))
if not self.BACK_ROOM_RE.match(entry.title.text):
return None
title_txt = self.BACK_ROOM_RE.sub('', entry.title.text)
show = Show()
show.venue = self.venue()
import re
from fancyashow.extensions import ExtensionLibrary, ShowParser
from fancyashow.extensions.models import Venue, Performer, Show
from fancyashow.util import parsing as html_util
from fancyashow.util import dates as date_util
from fancyashow.util import lang as lang_util
extensions = ExtensionLibrary()
class BrooklynBowl(ShowParser):
BASE_URL = "http://www.brooklynbowl.com/"
CALENDAR_URL = "http://www.brooklynbowl.com/calendar/"
IS_EVENT = re.compile("http://www.brooklynbowl.com/event/(?P<event_id>\d+)")
def __init__(self, *args, **kwargs):
super(BrooklynBowl, self).__init__(*args, **kwargs)
self._parser = None
def next(self):
if not self._parser:
self._parser = self._get_parser()
while True:
return self._parser.next()
raise StopIteration
def _get_parser(self):
show_urls = html_util.get_show_urls(self.CALENDAR_URL, ".list-view", ".list-view-item", self.IS_EVENT)
import subprocess
import logging
from tempfile import TemporaryFile
from fancyashow.extensions.artists import ArtistProcessor
from fancyashow.util.storage import ChunkedFile
from fancyashow.extensions import ExtensionLibrary
from datetime import datetime
from fancyashow.db.models import Audio, Video, MediaStatsHistory
from fancyashow.extensions.models import AudioInfo, VideoInfo
logger = logging.getLogger(__name__)
extensions = ExtensionLibrary()
class MediaExtractionProcessor(ArtistProcessor):
def __init__(self, library, settings):
super(MediaExtractionProcessor, self).__init__(library, settings)
self.update_interval = self.get_required_setting(settings, "update_interval")
@classmethod
def default_state(self):
return {"extractor_state": {}}
def process(self, artist, state, dependent_states):
new_state = self.clone_state(state)
media = []
import logging
import re
from datetime import datetime
from urllib2 import HTTPError
from fancyashow.extensions import ExtensionLibrary, ShowParser
from fancyashow.extensions.models import Venue, Performer, Show
from fancyashow.util import parsing as html_util
from fancyashow.util import dates as date_util
from fancyashow.util import lang as lang_util
logger = logging.getLogger(__name__)
extensions = ExtensionLibrary()
class CakeShop(ShowParser):
BASE_URL = "http://cake-shop.com/"
CALENDAR_RE = re.compile('%sshow-calendar/' % BASE_URL, re.IGNORECASE)
DATE_RE = re.compile("\w+\s+(?P<day>\d+)")
NUM_RE = re.compile('^\s*\d+\s*(?:st|nd|rd|th):\s*$', re.IGNORECASE | re.MULTILINE)
TIME_RE = re.compile('^\s*(?P<time>\d+(?::\d+)?\s*(?:am|pm))\s*', re.IGNORECASE | re.MULTILINE)
PRICE_OR_AGE = re.compile('(?:\$\d+|\d+\+)', re.IGNORECASE | re.MULTILINE)
MONTHS_AHEAD = 3
def __init__(self, *args, **kwargs):
super(CakeShop, self).__init__(*args, **kwargs)
self._current_parser = None
self._date_queue = self._request_dates()
def _next_parser(self):
if self._date_queue:
import re
import logging
from datetime import datetime, timedelta
from fancyashow.extensions import ExtensionLibrary, ShowParser
from fancyashow.extensions.models import Venue, Performer, Show
from fancyashow.util import parsing as html_util
from fancyashow.util import dates as date_util
from fancyashow.util import lang as lang_util
extensions = ExtensionLibrary()
logger = logging.getLogger(__name__)
class UnionHall(ShowParser):
BASE_URL = "http://www.unionhallny.com/"
CALENDAR_URL = "http://www.unionhallny.com/calendar.php"
DATE_RE = re.compile("\w+ (?P<month>\d+)/(?P<day>\d+):")
TIME_RE = re.compile(':\s+(?P<time>\d+(?:\s*:\s*\d+)?\s*[ap]\.?m\.?)\s*', re.IGNORECASE)
def __init__(self, *args, **kwargs):
super(UnionHall, self).__init__(*args, **kwargs)
self._parser = None
def next(self):
if not self._parser:
self._parse_started = datetime.now()
self._parser = self._get_parser()
while(True):
return self._parser.next()
