Last active
March 3, 2025 06:49
-
-
Save tanweerali/f0f31c20ff9dbd3cceb4185f93158de8 to your computer and use it in GitHub Desktop.
How to Scrape Tripadvisor data using ScrapingAnts Web Scraping API in Python
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 characters
| from bs4 import BeautifulSoup | |
| import http.client | |
| base_url = "https://www.tripadvisor.com/Hotels-g187768-Italy-Hotels.html" | |
| template_url = "https://www.tripadvisor.com/Hotels-g187768-oa{}-Italy-Hotels.html" | |
| num_pages = 2 | |
| urls = [base_url] | |
| for i in range(30, (num_pages * 30), 30): | |
| urls.append(template_url.format(i)) | |
| Hotel_Name = [] | |
| Hotel_Review = [] | |
| Hotel_Link = [] | |
| for url in urls: | |
| conn = http.client.HTTPSConnection("api.scrapingant.com") | |
| conn.request("GET", "/v2/general?url={}&x-api-key=68f2cb0e34564a9bb9fd2e93e84ff12d".format(url)) | |
| res = conn.getresponse() | |
| data = res.read() | |
| soup = BeautifulSoup(data, "html.parser") | |
| hotel_name = soup.find_all("div", attrs={"data-automation": "hotel-card-title"}) | |
| for name in hotel_name: | |
| Hotel_Name.append(name.text) | |
| for review in soup.find_all("div", attrs={"aria-label": True}): | |
| text = review["aria-label"] | |
| if "reviews" in text: | |
| Hotel_Review.append(text.split()[-2].replace(",", "")) | |
| hotel_link = soup.find_all("div", attrs={"data-automation": "hotel-card-title"}) | |
| for link in hotel_link: | |
| Hotel_Link.append('https://www.tripadvisor.com'+link.find('a')['href']) | |
| print(Hotel_Name) | |
| print(Hotel_Review) | |
| print(Hotel_Link) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment