def _get_parser(self):
doc = html_util.fetch_and_parse(self.BASE_URL)
events = html_util.get_first_element(doc, '.defaultText')
content = html_util.get_displayed_text_content(events).strip()
for line in content.split('\n'):
if self.SHOW_START_RE.match(line):
show = self._parse_show(line)
if show:
yield show
def _parse_show(self, date_txt, info_el):
logger.debug('Parsing show in %s' % date_txt)
info_txt = html_util.get_displayed_text_content(info_el)
performers = []
show_time_txt = None
for line in info_txt.split('\n'):
match = self.PERFORMER_RE.match(line)
if match:
time_txt, name = match.group('time'), match.group('performer')
show_time_txt = time_txt
performers.append(Performer(name, start_time = time_txt))
if len(performers) == 0:
return None
show = Show()
show.venue = self.venue()
show.performers = performers
show.show_time = date_util.parse_date_and_time(date_txt, show_time_txt)
show.resources.resource_uris = self.resource_extractor.extract_resources(info_el)
# Fontanas's stores the large image in an anchor tag
for a in info_el.iter(tag = 'a'):
if self.IMAGE_RE.search(a.get('href', '')):
show.resources.image_url = a.get('href')
date_util.adjust_fuzzy_years(show, self._parse_started)
return show
def _parse_show(self, event_detail):
show = Show()
performers = []
content = html_util.get_displayed_text_content(event_detail).strip()
date_txt = None
# This flag is set up and down to allow either of the following to be processed:
# 1st: Ava Luna
# or
# 1st:
# Ava Luna
had_num = True
logger.debug("Parsing show content: %s" % content)
for line in content.split('\n'):
if line:
time_match = date_util.STRICT_TIME_RE.search(line)
if not date_txt:
date_txt = line
elif time_match:
show.show_time = date_util.parse_date_and_time(date_txt, time_match.group('time'))
line = date_util.STRICT_TIME_RE.sub('', line).strip(': ')
if line:
performers.append(Performer(line))
had_num = False
else:
had_num = True
elif self.NUM_RE.match(line):
line = self.NUM_RE.sub('', line).strip()
if line:
performers.append(Performer(line))
had_num = False
else:
had_num = True
elif had_num:
performers.append(Performer(line))
had_num = False
else:
logger.error('Unknown line format: %s' % line)
show.venue = self.venue()
show.performers = performers
show.date = date_util.parse_date_and_time(date_txt, None)
show.resources.resource_uris = self.resource_extractor.extract_resources(event_detail)
for img_tag in event_detail.iter(tag = 'img'):
show.resources.image_url = img_tag.get('src')
break
date_util.adjust_fuzzy_years(show, self._parse_started)
return show
def TextMatcher(node, match_exp):
text = html_util.get_displayed_text_content(node)
for m in match_exp.finditer(text):
yield m