Closed desaismita closed 5 years ago
from lxml import html import requests
class AppCrawler:
def __init__(self,starting_url,depth): self.starting_url = starting_url self.depth = depth self.apps = [] def crawl(self): self.get_app_from_link(self.starting_url) return def get_app_from_link(self,Link): start_page = requests.get(Link) tree = html.fromstring(start_page.text) name = tree.xpath('//a[@class="link"]/text()') developer = tree.xpath('//div[@class="section__nav"]/h2/text()')[0] price = tree.xpath('//div[@class="l-row"]//*/h2/text()')[0] links = tree.xpath('//div[@class="section__nav"]//*/a[@class="link section__nav__see-all-link ember-view"]/@href') app = App(name,developer,price,links) self.apps.append(app) #print(links) return
class App: def init(self,name,developer,price,links): self.name = name self.developer = developer self.price = price self.links = links
def __str__(self): return('Name :' + self.name.encode('UTF-8') + '\r\nDeveloper :' + self.developer.encode('UTF-8') + '\r\nPrice :' + self.price.encode('UTF-8'))
crawler = AppCrawler("https://itunes.apple.com/us/app/candy-crush-saga/id553834731?mt=8", 0)
crawler.crawl()
for app in crawler.apps: print (app)
Can anybody help me know why am I getting this error?
Not a urlscan issue.
from lxml import html import requests
class AppCrawler:
class App: def init(self,name,developer,price,links): self.name = name self.developer = developer self.price = price self.links = links
crawler = AppCrawler("https://itunes.apple.com/us/app/candy-crush-saga/id553834731?mt=8", 0)
crawler.crawl()
for app in crawler.apps: print (app)