Successfully bypassed new Google Photos protection 🕺

config.py

@@ -5,7 +5,7 @@ cfg = dict(
 "review_loc_by_id": r'{}\",.*?\[\[null,null,(.*?),(.*?)\]'
 },
 
-headless = False, # if True, it doesn't show the browser while scraping GMaps reviews
+headless = True, # if True, it doesn't show the browser while scraping GMaps reviews
 ytb_hunt_always = False, # if True, search the Youtube channel everytime
 gmaps_radius = 30, # in km. The radius distance to create groups of gmaps reviews.
 gdocs_public_doc = "1jaEEHZL32t1RUN5WuZEnFpqiEPf_APYKrRBG9LhLdvE" # The public Google Doc to use it as an endpoint, to use Google's Search.

hunt.py

@@ -111,7 +111,7 @@ for user in data["matches"]:
 			else:
 				print("\nYoutube channel not found.")
 
-	gpics(gaiaID, client, cfg)
+	gpics(gaiaID, client, cookies, cfg)
 	reviews = gmaps.scrape(gaiaID, client, cookies, cfg)
 	if reviews:
 		confidence, locations = gmaps.get_confidence(reviews, cfg)

lib/photos.py

@@ -2,15 +2,108 @@ import httpx
 import re
 from io import BytesIO
 from lib.metadata import ExifEater
+from seleniumwire import webdriver
+from selenium.webdriver.chrome.options import Options
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
 from PIL import Image
+from lib.utils import *
 
 
-def gpics(gaiaID, client, cfg):
+def get_source(gaiaID, client, cookies, cfg):
+
+	baseurl = f"https://get.google.com/albumarchive/{gaiaID}/albums/profile-photos?hl=en"
+	req = client.get(baseurl)
+	if req.status_code != 200:
+		return False
+
+	class element_has_substring_or_substring(object):
+		"""An expectation for checking that an element has a particular css class.
+
+		locator - used to find the element
+		returns the WebElement once it has the particular css class
+		"""
+		def __init__(self, locator, substring1, substring2):
+			self.locator = locator
+			self.substring1 = substring1
+			self.substring2 = substring2
+			
+		def __call__(self, driver):
+			element = driver.find_element(*self.locator)   # Finding the referenced element
+			if self.substring1 in element.text:
+				return self.substring1
+			elif self.substring2 in element.text:
+				return self.substring2
+			else:
+				return False
+
+	tmprinter = TMPrinter()
+	chrome_options = Options()
+	chrome_options.add_argument('--log-level=3')
+	chrome_options.add_experimental_option('excludeSwitches', ['enable-logging'])
+	if cfg["headless"]:
+		chrome_options.add_argument("--headless")
+	options = {
+		'connection_timeout': None  # Never timeout, otherwise it floods errors
+	}
+
+	tmprinter.out("Starting browser...")
+
+	driverpath = get_driverpath()
+	driver = webdriver.Chrome(executable_path=driverpath, seleniumwire_options=options, options=chrome_options)
+	wait = WebDriverWait(driver, 30)
+
+	tmprinter.out("Setting cookies...")
+	driver.get("https://get.google.com/robots.txt")
+	for k,v in cookies.items():
+		driver.add_cookie({'name': k, 'value': v})
+
+	tmprinter.out('Fetching Google Photos "Profile photos" album...')
+	driver.get(f"https://get.google.com/albumarchive/{gaiaID}/albums/profile-photos?hl=en")
+
+	tmprinter.out('Fetching the Google Photos albums overview...')
+	buttons = driver.find_elements(By.XPATH, "//button")
+	for button in buttons:
+		text = button.get_attribute('jsaction')
+		if text and 'touchcancel' in text:
+			button.click()
+			break
+	else:
+		tmprinter.out("")
+		print("Can't get the back button..")
+		driver.close()
+		return False
+
+	wait.until(EC.text_to_be_present_in_element((By.XPATH, "//body"), "Album Archive"))
+	tmprinter.out("Got the albums overview !")
+	no_photos_trigger = "reached the end"
+	photos_trigger = " item"
+	result = wait.until(element_has_substring_or_substring((By.XPATH, "//body"), photos_trigger, no_photos_trigger))
+	if result == no_photos_trigger:
+		stats = "notfound"
+	else:
+		stats = "found"
+	tmprinter.out("")
+	source = driver.page_source
+	driver.close()
+
+	return {"stats": stats, "source": source}
+
+def gpics(gaiaID, client, cookies, cfg):
 	baseurl = "https://get.google.com/albumarchive/"
 
 	print(f"\nGoogle Photos : {baseurl + gaiaID}")
-	req = client.get(baseurl + gaiaID)
-	results = re.compile(cfg["regexs"]["albums"]).findall(req.text)
+	out = get_source(gaiaID, client, cookies, cfg)
+	if not out:
+		print("=> Couldn't fetch the public photos.")
+		return False
+	if out["stats"] == "notfound":
+		print("=> No album")
+		return False
+
+	#open('debug.html', 'w').write(repr(out["source"]))
+	results = re.compile(cfg["regexs"]["albums"]).findall(out["source"])
 
 	list_albums_length = len(results)