Add Image-scrapper script

Scripts/Web_Scrappers/Image_Scrapper/README.md

@@ -0,0 +1,23 @@
+# Images Scraper
+
+#### This script scrapes images from a URL and stores them on your local folder.
+
+# Pre-requisites:
+
+#### Run the following command:
+```bash
+pip install -r requirements.txt
+```
+# Instructions to run the script:
+
+#### Run the command:
+```python
+python Scraper.py
+```
+# Screenshot(images saved in local folder):
+
+![Output](https://user-images.githubusercontent.com/56406787/94802957-2b6fe380-0406-11eb-9d6a-b62b640c2c8d.png)
+
+# Author Name:
+
+[Rohit Joshi](https://github.com/rohitjoshi6)

Scripts/Web_Scrappers/Image_Scrapper/Scraper.py

@@ -1,25 +1,75 @@
-import requests
-from bs4 import BeautifulSoup
-import urllib.request
-import random
 import os
+import json 
+import requests # to sent GET requests
+from bs4 import BeautifulSoup # to parse HTML
 
-url="https://www.creativeshrimp.com/top-30-artworks-of-beeple.html"
+# user can input a topic and a number
+# download first n images from google image search
 
-source_code=requests.get(url)
+GOOGLE_IMAGE = \
+    'https://www.google.com/search?site=&tbm=isch&source=hp&biw=1873&bih=990&'
 
-plain_text=source_code.text
+# The User-Agent request header contains a characteristic string 
+# that allows the network protocol peers to identify the application type, 
+# operating system, and software version of the requesting software user agent.
+# needed for google search
+usr_agent = {
+    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11',
+    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+    'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.3',
+    'Accept-Encoding': 'none',
+    'Accept-Language': 'en-US,en;q=0.8',
+    'Connection': 'keep-alive',
+}
 
-soup=BeautifulSoup(plain_text)
+SAVE_FOLDER = 'images'
 
-
-for link in soup.find_all("a",{"class":"lightbox"}):
-    href=link.get('href')
-    print(href)
+def main():
+    if not os.path.exists(SAVE_FOLDER):
+        os.mkdir(SAVE_FOLDER)
+    download_images()
 
-    img_name=random.randrange(1,500)
+def download_images():
+    # ask for user input
+    data = input('What are you looking for? ')
+    n_images = int(input('How many images do you want? '))
+
+    print('Start searching...')
 
-    full_name=str(img_name)+".jpg"
+    # get url query string
+    searchurl = GOOGLE_IMAGE + 'q=' + data
+    print(searchurl)
+
+    # request url, without usr_agent the permission gets denied
+    response = requests.get(searchurl, headers=usr_agent)
+    html = response.text
+
+    # find all divs where class='rg_meta'
+    soup = BeautifulSoup(html, 'html.parser')
+    results = soup.findAll('div', {'class': 'rg_meta'}, limit=n_images)
 
-    urllib.request.urlretrieve(href,full_name)
-    print("Loop Break")
+    # extract the link from the div tag
+    imagelinks= []
+    for re in results:
+        text = re.text # this is a valid json string
+        text_dict= json.loads(text) # deserialize json to a Python dict
+        link = text_dict['ou']
+        # image_type = text_dict['ity']
+        imagelinks.append(link)
+
+    print(f'found {len(imagelinks)} images')
+    print('Start downloading...')
+
+    for i, imagelink in enumerate(imagelinks):
+        # open image link and save as file
+        response = requests.get(imagelink)
+
+        imagename = SAVE_FOLDER + '/' + data + str(i+1) + '.jpg'
+        with open(imagename, 'wb') as file:
+            file.write(response.content)
+
+    print('Done')
+
+
+if __name__ == '__main__':
+    main()

Scripts/Web_Scrappers/Image_Scrapper/requirements.txt

@@ -0,0 +1,5 @@
+requests
+bs4 
+BeautifulSoup
+urllib.request
+random