playwright nox

gistfile1.txt

from playwright.sync_api import sync_playwright

class NoxInfluencerCrawler(object):

    def crawl_details(self, detail_urls):
        with sync_playwright() as p:
            brower = p.chromium.launch(headless=False)
            context = brower.new_context()
            page = context.new_page()
            page.set_default_navigation_timeout(60*1000)

            login_url = "https://www.noxinfluencer.com/login?userType=brand&service=https%3A%2F%2Fwww.noxinfluencer.com%2F"

            page.goto(login_url)

            page.locator("#email").focus()
            page.keyboard.insert_text("[email protected]")

            page.locator("#pwd").focus()
            page.keyboard.insert_text("Q!w2e3r4")

            page.locator("#login-submit").click()

            page.wait_for_url("*noxinfluencer.com/youtube/search", timeout=60*1000)

            page.wait_for_timeout(5*1000)

            print(context.cookies)
            print(context.storage_state)

            results = []
            for detail_url in detail_urls:
                name = None
                youtube_url = None
                instagram_url = None
                fb_url = None
                tw_url = None
                tt_url = None

                try:
                    page.goto(detail_url)
                    page.wait_for_timeout(10*1000)
                except Exception as e:
                    print(e)
                    print(detail_url)
                    continue

                try:
                    name_selector = page.wait_for_selector(".info-block .title span", timeout=500)

                    if name_selector:
                        name = name_selector.text_content()
                except:
                    pass

                try:
                    youtube_url_selector = page.wait_for_selector("[sensors-name='social_ytb']", timeout=500)
                    if youtube_url_selector:
                        youtube_url = youtube_url_selector.get_attribute("href")
                except:
                    pass

                try:
                    instagram_url_selector = page.wait_for_selector("[sensors-name='social_ins']", timeout=500)
                    if instagram_url_selector:
                        instagram_url = instagram_url_selector.get_attribute("href")
                except:
                    pass

                try:
                    fb_url_selector = page.wait_for_selector("[sensors-name='social_fb']", timeout=500)
                    if fb_url_selector:
                        fb_url = fb_url_selector.get_attribute("href")
                except:
                    pass

                try:
                    tw_url_selector = page.wait_for_selector("[sensors-name='social_tw']", timeout=500)
                    if tw_url_selector:
                        tw_url = tw_url_selector.get_attribute("href")
                except:
                    pass

                try:
                    tt_url_selector = page.wait_for_selector("[sensors-name='social_tt']", timeout=500)
                    if tt_url_selector:
                        tt_url = tt_url_selector.get_attribute("href")
                except:
                    pass

                results.append((name, youtube_url, instagram_url, fb_url, tw_url, tt_url))
                if (len(results) <= 0):
                    print("error")
            return results

    def demo(self):
        with sync_playwright() as p:
            brower = p.chromium.launch(headless=False)
            page = brower.new_page()
            page.goto("https://www.noxinfluencer.com/youtube/channel/UCPFhnt7T8iaBLp1wIfFRzFw")