memeScraper1

imagexam.py

@@ -0,0 +1,21 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Sat Jan 19 16:15:00 2019
+
+@author: ADARSH ANURAG
+"""
+import pandas as pd
+import requests
+df = pd.read_csv("memedroid.csv")
+for x in df['image']:
+    overlay=True
+    url=x
+    payload = {'url': url,
+           'isOverlayRequired':overlay,
+           'apikey': '9ec509657e88957',
+           'language': 'eng',
+          }
+    r = requests.post('https://api.ocr.space/parse/image',data=payload,)
+    print(r.status_code, r.reason)
+    result = r.json()
+    print(['ParsedResults'][0]['ParsedText'])

memeScraper/memeScraper/items.py

@@ -0,0 +1,15 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class Meme(scrapy.Item):
+    # define the fields for your item here like:
+    title = scrapy.Field()
+    image = scrapy.Field()
+    tags = scrapy.Field()

memeScraper/memeScraper/middlewares.py

@@ -0,0 +1,103 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class MemescraperSpiderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(self, response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(self, response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, dict or Item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(self, response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Response, dict
+        # or Item objects.
+        pass
+
+    def process_start_requests(self, start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)
+
+
+class MemescraperDownloaderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the downloader middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_request(self, request, spider):
+        # Called for each request that goes through the downloader
+        # middleware.
+
+        # Must either:
+        # - return None: continue processing this request
+        # - or return a Response object
+        # - or return a Request object
+        # - or raise IgnoreRequest: process_exception() methods of
+        #   installed downloader middleware will be called
+        return None
+
+    def process_response(self, request, response, spider):
+        # Called with the response returned from the downloader.
+
+        # Must either;
+        # - return a Response object
+        # - return a Request object
+        # - or raise IgnoreRequest
+        return response
+
+    def process_exception(self, request, exception, spider):
+        # Called when a download handler or a process_request()
+        # (from other downloader middleware) raises an exception.
+
+        # Must either:
+        # - return None: continue processing this exception
+        # - return a Response object: stops process_exception() chain
+        # - return a Request object: stops process_exception() chain
+        pass
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

memeScraper/memeScraper/pipelines.py

@@ -0,0 +1,11 @@
+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+
+class MemescraperPipeline(object):
+    def process_item(self, item, spider):
+        return item

memeScraper/memeScraper/settings.py

@@ -0,0 +1,25 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for memeScraper project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     https://doc.scrapy.org/en/latest/topics/settings.html
+#     https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+#     https://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'memeScraper'
+
+SPIDER_MODULES = ['memeScraper.spiders']
+NEWSPIDER_MODULE = 'memeScraper.spiders'
+
+#Export as csv feed
+FEED_FORMAT = "csv"
+FEED_URI = "memedroid.csv"
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'memeScraper (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+ROBOTSTXT_OBEY = True

memeScraper/memeScraper/spiders/__init__.py

@@ -0,0 +1,4 @@
+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

memeScraper/memeScraper/spiders/memeSpider.py

@@ -0,0 +1,35 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Wed Dec 26 15:10:15 2018
+
+@author: ADARSH ANURAG
+"""
+from scrapy import Spider
+from scrapy.selector import Selector
+from memeScraper.items import Meme
+
+class MemeSpider(Spider):
+    name ="memebot"
+    allowed_domain = ["https://www.memedroid.com"]
+    start_urls = ["https://www.memedroid.com/memes/latest/"]
+
+    def parse(self,response):
+        Title=[]
+        Image=[]
+        Tags=[]
+        container = response.xpath("//div[@class='gallery-memes-container']")
+        articles = container.xpath(".//article")
+        for article in articles:
+            title = article.xpath(".//div[@class='item-aux-container']/header/h1/a/text()").extract()
+            Title.append(title[0])
+            image_link = article.xpath(".//div[@class='item-aux-container']/a[@class='dyn-link']/img/@src").extract()
+            Image.append(image_link[0])
+            tag = article.xpath(".//div[@class='tags-container']/a/text()").extract()
+            Tags.append(tag)
+            print('\n')
+        Item = Meme()
+        for item in zip(Title,Image, Tags):
+            Item['title'] = item[0]
+            Item['image'] = item[1]
+            Item['tags'] = item[2]
+            yield Item

memeScraper/scrapy.cfg

@@ -0,0 +1,11 @@
+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.io/en/latest/deploy.html
+
+[settings]
+default = memeScraper.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = memeScraper

purpose of memeScraper.md

@@ -0,0 +1,26 @@
+# Purpose of memeScraper:
+
+This Scraper scrapes the title, image and tags for a meme from https://www.memedroid.com.
+
+## Tools used:
+
+Scrapy
+
+## How to run:
+
+Run the memeSpider of memeScraper.
+Type this in command line
+```
+scrapy crawl memebot
+```
+
+## Output:
+
+This scraper returns title, image and tags for a meme in a csv file memedroid.csv.
+
+imagexam.py makes use of ocr space api to find texts inside the meme images for classification.
+
+## Future Works to be Performed:
+* Scrap memes from more websites.
+* Use of machine learning to provide relevant tags to meme without tags.
+* Make a suitable GUI for the resulting application.