Пример #1
0
def get_restaurant_reviews(file, url):
    # connecting to website
    browser = webdriver.Chrome(driver_location)
    browser.get(url=url)

    all_reviews = []

    # check if existing
    if scraper.has_results(browser.page_source):
        # skip welcome form
        if browser.find_element_by_id("zone_form"):
            welcome_form = browser.find_element_by_id("zone_form")
            welcome_form.submit()

        # check if there is next page
        try:
            while browser.find_element_by_id("nav_next_page"):
                page_reviews = scraper.get_page_data(browser.page_source, browser.current_url)
                all_reviews = all_reviews + page_reviews
                next_page = browser.find_element_by_id("nav_next_page")
                next_page.click()
        # no next page
        except:
            page_reviews = scraper.get_page_data(browser.page_source, browser.current_url)
            all_reviews = all_reviews + page_reviews

        print("Collected reviews for restaurant: " + url + " , now writing file: " + file)
        writer.write_reviews(file, all_reviews)

    else:
        print("Restaurant: " + url + " does not exist!")

    browser.quit()
    time.sleep(1)
    return len(all_reviews)
Пример #2
0
 def get(self):
     return {"data": get_page_data()}