|
@@ -2,17 +2,18 @@
|
|
|
|
|
|
from bs4 import BeautifulSoup
|
|
|
import cloudscraper
|
|
|
+import requests
|
|
|
|
|
|
def AleppoScraper():
|
|
|
-
|
|
|
+ url = "https://www.justeat.it/restaurants-saporedialeppo/menu"
|
|
|
+
|
|
|
scraper = cloudscraper.create_scraper(browser={'browser': 'firefox','platform': 'windows','mobile': False})
|
|
|
- page = scraper.get("https://www.justeat.it/restaurants-saporedialeppo/menu").content
|
|
|
- # with open('aleppo.html', 'wb') as f:
|
|
|
- # f.write(page)
|
|
|
+ page = scraper.get(url).content
|
|
|
|
|
|
- # scraper = cloudscraper.create_scraper(browser={'browser': 'firefox','platform': 'windows','mobile': False})
|
|
|
- # page = scraper.get("https://www.justeat.it/restaurants-bar-new-bridge-bologna/menu").content
|
|
|
- # with open('pandabao.html', 'wb') as f:
|
|
|
+ # headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'}
|
|
|
+ # page = requests.get(url, headers=headers).content
|
|
|
+
|
|
|
+ # with open('aleppo.html', 'wb') as f:
|
|
|
# f.write(page)
|
|
|
|
|
|
# with open('aleppo.html', 'rb') as f:
|