Merge pull request #104 from Apex-code/master

Added IMDB Spider

Author: AdityaJ7

Scripts/Web_Scrappers/IMDB-Mass-Scraper/.IMDB/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.

Scripts/Web_Scrappers/IMDB-Mass-Scraper/.IMDB/spiders/imdb_spider.py

@@ -0,0 +1,36 @@
+import scrapy
+from ..items import ImdbItem
+
+class QuotesSpider(scrapy.Spider):
+    name = "imdb"
+    page_number = 2
+    start_urls = [
+        'https://www.imdb.com/list/ls061697854'
+    ]
+
+    def parse(self, response):
+        items = ImdbItem()
+        title = response.css('.lister-item-header a::text').extract()
+        yearReleased = response.css('.text-muted.unbold::text').extract()
+        rating = response.css('.ipl-rating-star.small .ipl-rating-star__rating::text').extract()
+        votes = response.css('.text-muted+ span:nth-child(2)::text').extract()
+        totalGross = response.css('.text-muted .ghost~ .text-muted+ span::text').extract()
+        imageURL = response.css('#main .loadlate::attr(loadlate)').extract()
+        genre = response.css('.genre::text').extract()
+
+        
+        items['title'] = title
+        items['yearReleased'] = yearReleased
+        items['rating'] = rating  
+        items['votes'] = votes
+        items['totalGross'] = totalGross
+        items['imageURL'] = imageURL
+        items['genre'] = genre
+
+        yield items
+
+        next_page = 'https://www.imdb.com/list/ls061697854/?page=' + str(QuotesSpider.page_number)
+        if QuotesSpider.page_number < 32:
+            QuotesSpider.page_number += 1
+            yield response.follow(next_page, callback=self.parse)
+

Scripts/Web_Scrappers/IMDB-Mass-Scraper/IMDB

@@ -0,0 +1 @@
+Subproject commit 017229962c69eb5ff3de8612b4a4846da47eb130

Scripts/Web_Scrappers/IMDB-Mass-Scraper/README.md

@@ -0,0 +1,48 @@
+
+# IMDB Scraper 
+  - Scrap ALL Hollywood Hindi Dubbed Movies
+  - Saved Results Into DB or CSV
+  - Fast af
+.
+
+### Prerequisites
+
+* [Scrapy](https://scrapy.org/)-   Python framework for extracting the data.
+*  [pymongo](https://pymongo.readthedocs.io/en/stable/#)-  Module for working with MongoDB
+
+### Installation
+
+
+```sh
+Installing Scrapy
+$ pip3 intstall scrapy
+```
+
+
+
+
+
+```sh
+Installing pymongo
+$ pip3 install pymongo
+```
+
+
+
+
+# How to run the script
+ 1.  Git clone repo
+ 2. Goto Project_Directory/
+ 3. Open Terminal/cmd
+ 4. scrapy crawl imdb
+		
+		if you want output in csv add -o filename.csv to the command.
+
+
+### Screenshot/GIF showing the sample use of the script
+![scrapy cmd](imdb.gif)
+
+Author
+----
+
+Apex-Code

Scripts/Web_Scrappers/IMDB-Mass-Scraper/imdb.gif

@@ -0,0 +1,17 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class ImdbItem(scrapy.Item):
+    # define the fields for your item here like:
+    title = scrapy.Field()
+    yearReleased = scrapy.Field()
+    rating = scrapy.Field()
+    votes = scrapy.Field()
+    totalGross = scrapy.Field()
+    imageURL = scrapy.Field()
+    genre = scrapy.Field()

Scripts/Web_Scrappers/IMDB-Mass-Scraper/items.py

@@ -0,0 +1,103 @@
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+# useful for handling different item types with a single interface
+from itemadapter import is_item, ItemAdapter
+
+
+class ImdbSpiderMiddleware:
+    # 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, 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 Request 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 ImdbDownloaderMiddleware:
+    # 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)

Scripts/Web_Scrappers/IMDB-Mass-Scraper/middlewares.py

@@ -0,0 +1,25 @@
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html
+
+
+# useful for handling different item types with a single interface
+from itemadapter import ItemAdapter
+import  pymongo
+
+class ImdbPipeline:
+
+    def __init__(self):
+        self.conn = pymongo.MongoClient(
+            'localhost',
+            27017
+        )
+
+        db = self.conn['IMDB']
+        self.collection = db['IMDB']
+
+
+    def process_item(self, item, spider):
+        self.collection.insert(dict(item))
+        return item

Scripts/Web_Scrappers/IMDB-Mass-Scraper/pipelines.py

@@ -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 = IMDB.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = IMDB

Scripts/Web_Scrappers/IMDB-Mass-Scraper/scrapy.cfg

@@ -0,0 +1,88 @@
+# Scrapy settings for IMDB project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     https://docs.scrapy.org/en/latest/topics/settings.html
+#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'IMDB'
+
+SPIDER_MODULES = ['IMDB.spiders']
+NEWSPIDER_MODULE = 'IMDB.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+USER_AGENT = 'Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)'
+
+# Obey robots.txt rules
+ROBOTSTXT_OBEY = True
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+#DOWNLOAD_DELAY = 3
+# The download delay setting will honor only one of:
+#CONCURRENT_REQUESTS_PER_DOMAIN = 16
+#CONCURRENT_REQUESTS_PER_IP = 16
+
+# Disable cookies (enabled by default)
+#COOKIES_ENABLED = False
+
+# Disable Telnet Console (enabled by default)
+#TELNETCONSOLE_ENABLED = False
+
+# Override the default request headers:
+#DEFAULT_REQUEST_HEADERS = {
+#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+#   'Accept-Language': 'en',
+#}
+
+# Enable or disable spider middlewares
+# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'IMDB.middlewares.ImdbSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'IMDB.middlewares.ImdbDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See https://docs.scrapy.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+   'IMDB.pipelines.ImdbPipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See https://docs.scrapy.org/en/latest/topics/autothrottle.html
+#AUTOTHROTTLE_ENABLED = True
+# The initial download delay
+#AUTOTHROTTLE_START_DELAY = 5
+# The maximum download delay to be set in case of high latencies
+#AUTOTHROTTLE_MAX_DELAY = 60
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
+# Enable showing throttling stats for every response received:
+#AUTOTHROTTLE_DEBUG = False
+
+# Enable and configure HTTP caching (disabled by default)
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+#HTTPCACHE_ENABLED = True
+#HTTPCACHE_EXPIRATION_SECS = 0
+#HTTPCACHE_DIR = 'httpcache'
+#HTTPCACHE_IGNORE_HTTP_CODES = []
+#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'