def __init__(self):
BaseScraper.__init__(self)
self.html_scraper = ScrapeTrailPeakRawHTML()
self.gpx_scraper = ScrapeTrailPeakGPX()
self.html_scraper.debug = False
self.base_url = "https://www.trailpeak.com/index.jsp?con=trail&val="
self.wait = 0
def __init__(self, *args, **kwargs):
BaseScraper.__init__(self, *args, **kwargs)
if self.template_url is None:
raise ValueError("%s must have a template_url attribute" % self.__class__.__name__)
self.request_manager = FastRequestManager()
response = self.request_manager.make_request(self.template_url)
self.template_html_schema = self._get_html_schema(response.raw_html)
def __init__(self, *args, **kwargs):
BaseScraper.__init__(self, *args, **kwargs)
if self.template_url is None:
raise ValueError("%s must have a template_url attribute" %
self.__class__.__name__)
self.request_manager = FastRequestManager()
response = self.request_manager.make_request(self.template_url)
self.template_html_schema = self._get_html_schema(response.raw_html)
def get_uncached_content(self, url):
trail_id = url.replace(self.base_url, "")
html_url = self.base_url+trail_id
html = self.html_scraper.item_content(html_url)
for line in html.split("\n"):
if "GPX_URL" in line:
name = line.split("\"")[1]
if name is not "":
gpx_url = "https://www.trailpeak.com/content/gpsData/gps{}-{}.gpx".format(trail_id, name)
data = BaseScraper.get_uncached_content(self, gpx_url)
return data
return ""
def __init__(self):
BaseScraper.__init__(self)
self.base_url = "https://www.trailpeak.com/index.jsp?con=trail&val="
def _validate(self, response):
return BaseScraper._validate(self, response) and self._compare_with_template(response)
def _validate(self, response):
return BaseScraper._validate(
self, response) and self._compare_with_template(response)