def stage_detail_parse(stage_number,url):
data={}
urlfetch.set_default_fetch_deadline(45)
images_json=[]
data_order=["day","month","avg-speed","cat","start-finish"]
page = urllib2.urlopen(url)
soup = BeautifulSoup(page, "html.parser")
tabulka = soup.find("h3", {"class" : "section"})
div = tabulka.parent
images = soup.findAll('img')
for image in images:
if "Stage" in image["src"]:
images_json.append(image["src"])
if "Final_GC" in image["src"]:
images_json.append(image["src"])
if "site-icons" in image["src"]:
data['stage-icon']=image["src"]
cont=0
data['stage-images']=images_json
for element in tabulka.parent:
if(cont<len(data_order)):
if element.name is None and "\n" not in element.string and element.string !=" " and "Tag for network 919" not in element.string:
#The interesting information doesn't have a tag
data[data_order[cont]]=element.string
cont+=1
print stage_number
stage=Stage.get_by_id(int(stage_number))
stage_data=json.loads(stage.data)
stage_data.update(data)
stage.data=json.dumps(stage_data)
stage.put()
