def do_GET(self):
try:
action, fields = self.__validate(self.path)
if action == '/ping':
self._set_headers()
self.wfile.write('OK')
return
else:
key = (fields['video_type'], fields['trakt_id'],
fields.get('season'), fields.get('episode'))
if action == '/clear':
with self.lock:
if key in self.proxy_cache:
del self.proxy_cache[key]
self._set_headers()
self.wfile.write('OK')
return
else:
with self.lock:
if key in self.proxy_cache:
images = self.proxy_cache[key]
else:
video_ids = json.loads(fields['video_ids'])
if fields[
'video_type'] == image_scraper.OBJ_PERSON:
person_ids = json.loads(fields['person_ids'])
person = {
'person': {
'name': fields['name'],
'ids': person_ids
}
}
images = image_scraper.scrape_person_images(
video_ids, person)
else:
images = image_scraper.scrape_images(
fields['video_type'], video_ids,
fields.get('season', ''),
fields.get('episode', ''))
self.proxy_cache[key] = images
image_url = images[fields['image_type']]
if image_url is None:
self._set_headers()
elif image_url.startswith('http'):
self.__redirect(image_url)
else:
self._set_headers()
if self.command == 'GET':
with open(image_url) as f:
self.wfile.write(f.read())
except ValidationError as e:
self.__send_error(e)
def imscrap(site):
import image_scraper
image_scraper.scrape_images(site)
print ("SOM RTUUTU")
import image_scraper
image_scraper.scrape_images(
"http://st.ourhtmldemo.com/new/Shelder1/assets/images/icons/")
from bs4 import BeautifulSoup as BS
import urllib.request
import certifi
import image_scraper
with urllib.request.urlopen("https://www.deere.com/en/index.html", cafile=certifi.where()) as url:
html = url.read()
soup = BS(html,'html.parser')
#for link in soup.find_all('a'):
#print(link.get('href'))
#for link in soup.find_all('div'):
#print(link.attrs['class'].['industry-img'])
imglinks = []
for imglink in soup.find_all('img'):
print(imglink.attrs['src'])
imglinks.append(imglink.attrs['src'])
print(imglinks)
image_scraper.scrape_images('https://github.com')
import image_scraper #image_scraper.scrape_images(URL)
url = str(input("URL="))
lang=str(input('lang='))
tagval=len(url.split("/"))
image_scraper.scrape_images(url) -s ./raw/
import image_scraper
import randomword
import os
path = 'E:\Python Workspace\Scrap specilized\Images'
image_scraper.scrape_images('https://imgur.com/',40,["jpg","png","gif","jpeg"],path,10000,False,False)
imgs_url = []
for file in glob.glob('*.jpg'):
imgs_url += [file.replace('.jpg', '')]
print(imgs_url)
print(len(imgs_url))
'''
https://static.wixstatic.com/media/d4a7a2_1fecc1f8206b4de0ad9baafc055eee83.jpg/v1/fill/w_1000,h_1000,al_c,q_90/d4a7a2_1fecc1f8206b4de0ad9baafc055eee83.webp
'''
prefix = 'https://static.wixstatic.com/media/{}.jpg/v1/fill/w_1000,h_1000,al_c,q_90/{}.webp'
for url in imgs_url:
image_scraper.scrape_images(prefix.format(url, url))
'''
# class instantiation
response = google_images_download.googleimagesdownload()
# creating list of arguments
arguments = {'url': prefix.format(url, url), 'format': 'webp',
'print_urls': True, 'usage_rights': 'labeled-for-nocommercial-reuse'}
# passing the arguments to the function
paths = response.download(arguments)
# printing absolute paths of the downloaded images
print(paths)
'''
import image_scraper URL = './' imgs = image_scraper.scrape_images(URL) print(imgs)
#pip install ImageScraper
import image_scraper
#this uses python3
max = input("How many pepe images do you want to download - not currently working")
source = input("From which sources should images be imported")
path = input("Add the path of test_images folder - not currently working")
image_scraper.scrape_images(source)
import image_scraper
rc_base_url = "https://redislabs.com/redis-cloud-documentation/"
image_scraper.scrape_images(
"https://redislabs.com/redis-cloud-documentation/overview/")
rc = open("rc_urls.txt", "r")
for line in rc.readlines():
url = rc_base_url + line
print(url)
image_scraper.scrape_images(url)
def downloadImages(url):
scrape_images(url, download_path='./images/')
