i am learning how to scrape data from booking using python and i get this error for this line :

 for h in data["hotels"]:

'NoneType' object is not iterable

This is my code :

e = Extractor.from_yaml_file('C:/Users/pc/OneDrive/Bureau/booking-hotel-scraper-master/booking.yml')

def scrape(url):    
    headers = {
        'Connection': 'keep-alive',
        'Pragma': 'no-cache',
        'Cache-Control': 'no-cache',
        'DNT': '1',
        'Upgrade-Insecure-Requests': '1',
        # You may want to change the user agent if you get blocked
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.113 Safari/537.36',
        'Accept': 'text/html,application/xhtml xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',

        'Referer': 'https://www.booking.com/index.en-gb.html',
        'Accept-Language': 'en-GB,en-US;q=0.9,en;q=0.8',
    }
     # Download the page using requests
    print("Downloading %s"%url)
    r = requests.get(url, headers=headers)
    # Pass the HTML of the page and create 
    return e.extract(r.text,base_url=url)

with open("C:/Users/pc/OneDrive/Bureau/booking-hotel-scraper-master/urls.txt",'r') as urllist, open('C:/Users/pc/OneDrive/Bureau/booking-hotel-scraper-master/data.csv','w') as outfile:
    fieldnames = [
        "name",
        "location",
        "price",
        "room_type",
        "beds",
        "number_of_ratings",
        "url"
    ]
    writer = csv.DictWriter(outfile, fieldnames=fieldnames,quoting=csv.QUOTE_ALL)
    writer.writeheader()
    for url in urllist.readlines():
        data = scrape(url) 
        if data:
            for h in data["hotels"]:
                writer.writerow(h)

CodePudding user response：

You can try this:

for h in data["hotels"] if h else None:

CodePudding user response：

You can check if data has hotels or not before looping

if data and data['hotels'] is not None: 
    for h in data["hotels"]:
        writer.writerow(h)