summaryrefslogtreecommitdiffstats
path: root/ddg-imager-taker
diff options
context:
space:
mode:
Diffstat (limited to 'ddg-imager-taker')
-rwxr-xr-xddg-imager-taker91
1 files changed, 91 insertions, 0 deletions
diff --git a/ddg-imager-taker b/ddg-imager-taker
new file mode 100755
index 0000000..c68817f
--- /dev/null
+++ b/ddg-imager-taker
@@ -0,0 +1,91 @@
+#!/usr/bin/python3
+import argparse
+import urllib.request
+from os.path import basename
+
+parser = argparse.ArgumentParser(add_help=True)
+parser.add_argument('--output','-o',
+ default=".",
+ dest='outputDir',
+ action="store",
+ help="location to save to",
+ type=str
+ )
+parser.add_argument('--amount','-a',
+ default=100,
+ dest='amount',
+ action="store",
+ help="the amount of images you'd like to download",
+ type=int
+ )
+parser.add_argument('URLs',
+ nargs='+',
+ type=str,
+ help='Site to query'
+ )
+
+
+
+args = parser.parse_args()
+
+from time import sleep
+from selenium import webdriver
+from selenium.webdriver.chrome.options import Options
+from selenium.webdriver.common.by import By
+chrome_options = Options()
+chrome_options.add_argument("--headless")
+driver = webdriver.Chrome(options=chrome_options)
+SourceURLs=[]
+driver.implicitly_wait(1)
+
+def getSource():
+ print("Opening...")
+ AllPortraitThumbnails[element].click()
+ SourceURLs.append(driver.find_element(By.XPATH, "/html/body/div[2]/div[3]/div/div[2]/div/div[1]/div[1]/div/div[2]/div/div/a").get_attribute('href'))
+
+
+for url in args.URLs:
+ driver.get(url)
+ sleep(3)
+ AllPortraitThumbnails = driver.find_elements(By.XPATH, "/html/body/div[2]/div[3]/div/div[1]/div[2]/div/./div")
+
+ for element in range(args.amount):
+ print("Obtaining element number " + str(element))
+ try:
+ if element % 100 == 0 and element != 0:
+ sleep(5)
+ getSource()
+ else:
+ getSource()
+ except:
+ AllPortraitThumbnails = driver.find_elements(By.XPATH, "/html/body/div[2]/div[3]/div/div[1]/div[2]/div/./div")
+ sleep(5)
+
+
+print("Starting Download...")
+driver.quit()
+
+
+for sourceURL in SourceURLs:
+ name = basename(sourceURL)
+ try:
+ print("Downloading " + name)
+ urllib.request.urlretrieve(sourceURL, args.outputDir + "/" + name)
+ except KeyboardInterrupt:
+ print("KeyboardInterrupt Detected!")
+ driver.quit()
+ quit(1)
+ except:
+ pass
+
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License version 3 as published by
+# the Free Software Foundation.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program. If not, see <https://www.gnu.org/licenses/>.