def summary(self):
"""parses the episode's summary from the episode's tvrage page"""
try:
if timeout:
page = _fetch(self.link, timeout=timeout).read()
else:
page = _fetch(self.link).read()
if not 'Click here to add a summary' in page:
summary = parse_synopsis(page, cleanup='var addthis_config')
return summary
except Exception, e:
print('Episode.summary: %s, %s' % (self, e))
def synopsis(self):
"""scraps the synopsis from the show's tvrage page using a regular
expression. This method might break when the page changes. unfortunatly
the episode summary isnt available via one of the xml feeds"""
try:
if timeout:
page = _fetch(self.link, timeout=timeout).read()
else:
page = _fetch(self.link).read()
synopsis = parse_synopsis(page)
return synopsis
except Exception, e:
logger.error('Show.synopsis:urlopen: %s, %s' % (self, e))
def _fetch_xml(url, node=None, timeout=None):
"""fetches the response of a simple xml-based webservice. If node is
omitted the root of the parsed xml doc is returned as an ElementTree object
otherwise the requested node is returned"""
if timeout:
xmldoc = _fetch(url, timeout=timeout)
else:
xmldoc = _fetch(url)
result = et.parse(xmldoc)
root = result.getroot()
if not node:
retval = root
else:
retval = root.find(node)
return retval
def recap(self):
"""parses the episode's recap text from the episode's tvrage recap
page"""
try:
if timeout:
page = _fetch(self.recap_url, timeout=timeout).read()
else:
page = _fetch(self.recap_url).read()
if not 'Click here to add a recap for' in page:
recap = parse_synopsis(page,
cleanup='Share this article with your'
' friends')
return recap
except Exception, e:
logger.error('Episode.recap:urlopen: %s, %s' % (self, e))
def fetch(show, exact=False, ep=None):
query_string = '?show=' + quote(show)
if exact:
query_string = query_string + '&exact=1'
if ep:
query_string = query_string + '&ep=' + quote(ep)
resp = _fetch(BASE_URL + query_string).read()
show_info = {}
if 'No Show Results Were Found For' in resp:
raise ShowNotFound(show)
else:
data = resp.replace('<pre>', '').splitlines()
for line in data:
ne in data:
try:
if '@@' in line:
line = line.replace('@@','@')
k, v = line.split('@')
v = '@' + v
else:
k, v = line.split('@')
except ValueError, err:
except ValueError, err: #"Ended@"
k = line.replace('@',"")
v = ""
def summary(self):
"""parses the episode's summary from the episode's tvrage page"""
try:
page = _fetch(self.link).read()
if not 'Click here to add a summary' in page:
summary = parse_synopsis(page, cleanup='var addthis_config')
return summary
except Exception, e:
print('Episode.summary: %s, %s' % (self, e))
def synopsis(self):
"""scraps the synopsis from the show's tvrage page using a regular
expression. This method might break when the page changes. unfortunatly
the episode summary isnt available via one of the xml feeds"""
try:
page = _fetch(self.link).read()
synopsis = parse_synopsis(page)
return synopsis
except Exception, e:
print('Show.synopsis:urlopen: %s, %s' % (self, e))
def _fetch_xml(url, node=None):
"""fetches the response of a simple xml-based webservice. If node is
omitted the root of the parsed xml doc is returned as an ElementTree object
otherwise the requested node is returned"""
xmldoc = _fetch(url)
result = et.parse(xmldoc)
root = result.getroot()
if not node:
retval = root
else:
retval = root.find(node)
return retval
def recap(self):
"""parses the episode's recap text from the episode's tvrage recap
page"""
try:
page = _fetch(self.recap_url).read()
if not 'Click here to add a recap for' in page:
recap = parse_synopsis(page,
cleanup='Share this article with your'
' friends')
return recap
except Exception, e:
print('Episode.recap:urlopen: %s, %s' % (self, e))
def fetch(show, exact=False, ep=None, timeout=None):
query_string = '?show=' + quote(show)
if exact:
query_string += '&exact=1'
if ep:
query_string += '&ep=' + quote(ep)
if timeout is None:
resp = _fetch(BASE_URL + query_string).read()
else:
resp = _fetch(BASE_URL + query_string, timeout=timeout).read()
show_info = {}
if 'No Show Results Were Found For' in resp:
raise ShowNotFound(show)
else:
data = resp.replace('<pre>', '').splitlines()
for line in data:
splits = line.split('@')
k, v = splits[0], '@'.join(splits[1:])
# TODO: use datetimeobj for dates
show_info[k] = (v.split(' | ') if ' | ' in v else
(v.split('^') if '^' in v else v))
return show_info
def fetch(show, exact=False, ep=None):
query_string = '?show=' + quote(show)
if exact:
query_string = query_string + '&exact=1'
if ep:
query_string = query_string + '&ep=' + quote(ep)
resp = _fetch(BASE_URL + query_string).read()
show_info = {}
if 'No Show Results Were Found For' in resp:
raise ShowNotFound(show)
else:
data = resp.replace('<pre>', '').splitlines()
for line in data:
k, v = line.split('@')
# TODO: use datetimeobj for dates
show_info[k] = (v.split(' | ') if ' | ' in v else
(v.split('^') if '^' in v else v))
return show_info
