Created
March 23, 2018 14:09
-
-
Save cubedtear/e825f5eb9f77f18e40756ad8a1a14e4d to your computer and use it in GitHub Desktop.
Revisions
-
cubedtear created this gist
Mar 23, 2018 .There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode charactersOriginal file line number Diff line number Diff line change @@ -0,0 +1,32 @@ import requests from lxml import html, etree item_prices = [] for page in range(1, 10): r = requests.get('https://www.chollometro.com/nuevos', {'page': str(page), 'ajax': 'true'}) res = html.fromstring(r.text) items = res.xpath('//div[contains(@class, "threadCardLayout--card")]') for item in items: t = etree.tostring(item) if item.xpath('.//article[contains(@class, "thread--expired")]'): continue price_elems = item.xpath('.//span[contains(@class, "thread-price")]') if not price_elems: continue title_elem = item.xpath('.//strong[contains(@class, "thread-title")]/span/a') title = title_elem[0].text.strip() price = price_elems[0].text.replace("€", "").replace(",", ".") try: item_prices.append((title, float(price), title_elem[0].attrib['href'])) except ValueError: pass item_prices.sort(key=lambda x: x[1]) longest = len(max(item_prices, key=lambda x: len(x[0]))[0]) for title, price, url in item_prices: print("{price:7} - {title:{width}s} - {url}".format(title=title, price=price, url=url, width=longest))