Jocaru/amazon-telegram
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Syncing old changes...

Browse Source
This commit is contained in:
Joan
2023-08-28 20:51:29 +02:00
parent d99399f6ac
commit e124ca4f2f
2 changed files with 15 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
bot/bot.py
View File

@@ -53,14 +53,17 @@ def find_amazon_link(update: Update, context: CallbackContext) -> None:
user, chat, message_id = update.message.from_user, update.message.chat, update.message.message_id
logging.info(f"Link sent by {user} - {msg}")
referurl = helpers.new_refer_url(productCode, extraparams)
logging.info("Setting up new Chrome Browser")
driver = webdriver.Chrome(options=get_chrome_options())
driver.set_window_size(random.randint(1200, 1800), random.randint(600, 1000))
logging.info("Loading Amazon webpage")
driver.get(msg)
driver.get(referurl)
logging.info("Scraping information and closing browser")
soup = BeautifulSoup(driver.page_source, "lxml")
etree_soup = BeautifulSoup(driver.page_source, "html.parser")
# DEBUG
#logging.info(soup)
logging.info("Getting title...")
title, price, image = parser.get_title(soup), parser.get_price(soup), parser.get_image(soup, etree_soup)
@@ -93,7 +96,6 @@ def find_amazon_link(update: Update, context: CallbackContext) -> None:
driver.close()
context.bot.deleteMessage(chat_id=chat['id'], message_id=message_id)
referurl = helpers.new_refer_url(productCode, extraparams)
product_id = dbhelper.check_product(referurl, price)
if not product_id:
product_id = dbhelper.add_product(user['username'], chat['title'], user['id'], chat['id'], msg, referurl, title, price, image)

9
bot/parser.py
View File

@@ -40,8 +40,17 @@ def get_image(soup, etree_soup):
dom = etree.HTML(str(etree_soup))
image = dom.xpath('//*[@id="main-image-container"]/ul/li[4]/span/span/div/img')
image = image[0].get('src')
except IndexError:
logging.info("Couldn't retrieve image, trying with xpath method")
dom = etree.HTML(str(etree_soup))
image = dom.xpath('//*[@id="main-image-container"]/ul/li[5]/span/span/div/img')
image = image[0].get('src')
except AttributeError:
logging.info("Couldn't retrieve image with xpath method, falling back to placeholder")
image = "N/A"
except Exception as e:
logging.info(f"Error retrieving image: {e}")
except Exception as e:
logging.info(f"Error retrieving image: {e}")
return image