def _parse_show(self, show_date, show_detail, show_time):
show = Show()
time_txt = ','.join([p for p in show_time.text_content().split(',') if not self.PRICE_OR_AGE.search(p)])
logger.debug('Show: %s - %s' % (time_txt, show_time.text_content().strip(' \n')))
show.venue = self.venue()
show.performers = self._parse_performers(show_detail)
show.show_time = date_util.parse_show_time(show_date, time_txt)
show.door_time = date_util.parse_door_time(show_date, time_txt)
# TODO right now the below parsing doesn't work, so just skip these shows for now
if not show.show_time and not show.door_time:
time_match = self.TIME_RE.search(time_txt)
if time_match:
show.door_time = date_util.parse_date_and_time(show_date, time_match.group('time'))
show.resources.resource_uris = self.resource_extractor.extract_resources(show_detail, show_time)
# TODO work could be done here to find larger images (sometimes the img's are enclosed in an anchor tag)
for img_tag in show_detail.iter(tag = 'img'):
src = img_tag.get('src')
# Skip the images that show the early shows, later shows, and the 5 years logo
if not ('early' in src or 'later' in src or '5years' in src):
show.resources.image_url = src
break
return show
def _parse_show(self, el):
event_detail = html_util.get_first_element(el, '.event-details')
date_txt = html_util.get_first_element(event_detail, 'strong').text
time_txt = event_detail.text_content()
show = Show()
show.venue = self.venue()
title_txt = html_util.get_first_element(event_detail, '.event-name').text_content()
show.performers = [Performer(p) for p in lang_util.parse_performers(title_txt)]
show.show_time = date_util.parse_show_time(date_txt, time_txt)
show.door_time = date_util.parse_door_time(date_txt, time_txt)
show.resources.resource_uris = self.resource_extractor.extract_resources(event_detail)
img = html_util.get_first_element(el, ".event-image img", optional = True)
if img is not None:
show.resources.image_url = img.get('src')
date_util.adjust_fuzzy_years(show, self._parse_started)
return show
def _parse_show(self, link):
event_doc = html_util.fetch_and_parse(link)
event_detail = event_doc.get_element_by_id("eventDetail")
title_txt = []
found_h_el = False
# Start parsing when we find the first h* element
# Stop parsing if we found an h* element, but then encounter anything else
for el in event_detail.getchildren():
if el.tag in ("h1", "h2"):
found_h_el = True
if el.text_content():
title_txt.append(el.text_content())
elif found_h_el:
break
"""
<span id="timeDetail">
Apr 24, 2010<br />
upstairs<br />
Doors @ 7 PM<br/>
$15.00 Adv. / $20 at the Door<br />
<a href="http://www.deadcellentertainment.tix.com/Schedule.asp?OrganizationNumber=2690" target="_blank">
<img src="/images/buyticket.png" alt="Purchase Tickets" />
</a>
</span>
"""
time_el = event_detail.get_element_by_id("timeDetail")
date_txt = time_el.text
time_txt = time_el.text_content()
performers = []
show = Show()
show.merge_key = link
show.venue = self.venue()
show.performers = [Performer(p) for p in lang_util.parse_performers("/".join(title_txt))]
show.door_time = date_util.parse_show_time(date_txt, time_txt)
show.show_time = date_util.parse_door_time(date_txt, time_txt)
show.resources.show_url = link
show.resources.resource_uris = self.resource_extractor.extract_resources(event_detail)
img = html_util.get_first_element(event_detail, "img")
if img is not None:
show.resources.image_url = img.get("src")
return show
def _parse_show(self, link):
event_doc = html_util.fetch_and_parse(link)
event = html_util.get_first_element(event_doc, '#tfly-center-column-wide')
event_detail = html_util.get_first_element(event, '#details')
"""
<div class="info">
Sat, May 22, 2010<br />
Doors: 6:00 PM / Show: 7:00 PM <br />
$5.00<br />
</div>
"""
event_info = html_util.get_first_element(event_detail, ".info")
date_txt = event_info.text
time_txt = event_info.getchildren()[0].tail
img = html_util.get_first_element(event_detail, "img")
performers = []
for tag in ('h1', 'h2', 'h3', 'h4'):
for h in event_detail.iter(tag = tag):
performers.extend(self._parse_performers(h))
show = Show()
show.merge_key = link
show.venue = self.venue()
show.performers = performers
show.show_time = date_util.parse_show_time(date_txt, time_txt)
show.door_time = date_util.parse_door_time(date_txt, time_txt)
show.resources.show_url = link
show.resources.resource_uris = self.resource_extractor.extract_resources(event)
if img is not None:
show.resources.image_url = img.get('src')
return show
def _parse_show(self, link, show_section):
show_doc = html_util.fetch_and_parse(link)
show_detail = html_util.get_first_element(show_doc, "#content .event-detail")
date_txt = html_util.get_first_element(show_detail, ".dates").text_content()
time_txt = html_util.get_first_element(show_detail, ".times").text_content()
sold_out = html_util.get_first_element(show_detail, '.sold-out', optional = True)
image = html_util.get_first_element(show_detail, 'img', optional = True)
# The image we want is generally the first one, but if the layout changes this may break
if image is not None:
image_url = image.get('src')
else:
image_url = None
performers = []
for tag in ('h1', 'h2', 'h3'):
for p in show_detail.iter(tag = tag):
if p.text_content():
performers.extend(self._parse_performers(p))
show = Show()
show.merge_key = link
show.venue = self.venue()
show.performers = performers
show.door_time = date_util.parse_door_time(date_txt, time_txt)
show.show_time = date_util.parse_show_time(date_txt, time_txt)
show.soldout = sold_out is not None
show.resources.show_url = link
show.resources.image_url = image_url
show.resources.resource_uris = self.resource_extractor.extract_resources(show_detail)
return show
def _parse_show(self, link):
event_doc = html_util.fetch_and_parse(link)
match = self.IS_EVENT.match(link)
event_id = int(match.group("event_id"))
event_detail = html_util.get_first_element(event_doc, ".tfly-event-id-%d" % event_id)
date_txt = html_util.get_first_element(event_doc, ".dates").text_content()
time_txt = html_util.get_first_element(event_doc, ".times").text_content()
img = html_util.get_first_element(event_detail, "img")
performers = []
for p in html_util.get_elements(event_detail, ".headliners"):
performers.append(Performer(p.text_content(), headliner=True))
for p in html_util.get_elements(event_detail, ".supports"):
for pi in lang_util.parse_performers(p.text_content()):
performers.append(Performer(pi, headliner=False))
show = Show()
show.merge_key = link
show.venue = self.venue()
show.performers = performers
show.show_time = date_util.parse_show_time(date_txt, time_txt)
show.door_time = date_util.parse_door_time(date_txt, time_txt)
show.resources.show_url = link
show.resources.resource_uris = self.resource_extractor.extract_resources(event_detail)
if img is not None:
show.resources.image_url = img.get("src")
return show