initial version

README.md

@@ -1,13 +1,16 @@
----
-title: Law Finder Ipc
-emoji: 📚
-colorFrom: pink
-colorTo: green
-sdk: streamlit
-sdk_version: 1.9.0
-app_file: app.py
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference
+# IPC Semantic Search
+
+**What:**
+- The Indian Penal Code (IPC) is the official criminal code of India. [Wikipedia](https://en.wikipedia.org/wiki/Indian_Penal_Code)
+- The intention behind this project is to provide an interfact for a common layman to search IPC sections.
+
+**Steps:**
+- Scrap the `devgan.in` website to get the different sections in IPC
+- Use `LegalBERT` to get the embeddings of the descriptions of the IPC sections
+- Perform Cosine Similarity to get the nearest matching section wrt query.
+
+**Code:**
+- `devganscrap`: Scrapy code to crawl and extract IPC sections and their description from the `devgan.in`
+
+**Data:**
+- `devagnscrp/sections_desc.csv`: IPC sections and descriptions *(Data Credits: http://devgan.in)*

app.py

@@ -0,0 +1,42 @@
+# import
+import pandas as pd
+import streamlit as st
+from txtai.embeddings import Embeddings
+
+# set config
+st.set_page_config(layout="wide", page_title="⚖️ Law Finder - IPC")
+
+# load the summarization model (cache for faster loading)
+@st.cache(allow_output_mutation=True)
+def load_model_embeddings_data():
+    embeddings = Embeddings({"path": "sentence-transformers/nli-mpnet-base-v2"})
+    # embeddings.load("embedding")
+    df = pd.read_csv("devganscrap/sections_desc.csv")
+    embeddings.index([(uid, str(text), None) for uid, text in enumerate(df['description'].tolist())]) 
+    return embeddings, df
+
+# loading the model
+embeddings, df = load_model_embeddings_data()
+
+# APP
+# set title and subtitle
+st.title("⚖️ Law Finder - IPC")
+st.markdown("Search the [Indian Penal Code](https://en.wikipedia.org/wiki/Indian_Penal_Code) Sections with simple english.")
+st.markdown("The data scraping procedure is explained in detail on [my website](http://mohitmayank.com/a_lazy_data_science_guide/python/scraping_websites/)")
+st.markdown("The complete code is on [Github](https://github.com/imohitmayank/ipc_semantic_search)")
+
+# create the input text box
+query = st.text_area("Input your search phrase here!", "animal cruelty")
+button = st.button("Find sections...")
+
+# if button is clicked
+with st.spinner("Finding the most similar sections...."):
+    if button:
+        # find and display the sections
+        st.markdown("**Sections:**")
+        results = []
+        for id, score in embeddings.search(query, limit=5):
+            st.write({
+                'section': df.loc[id, 'section'],
+                'description': df.loc[id, 'description']
+            })

devganscrap/devganscrap/items.py

@@ -0,0 +1,12 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class DevganscrapItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

devganscrap/devganscrap/middlewares.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 DevganscrapSpiderMiddleware:
+    # 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 DevganscrapDownloaderMiddleware:
+    # 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)

devganscrap/devganscrap/pipelines.py

@@ -0,0 +1,13 @@
+# 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
+
+
+class DevganscrapPipeline:
+    def process_item(self, item, spider):
+        return item

devganscrap/devganscrap/settings.py

@@ -0,0 +1,88 @@
+# Scrapy settings for devganscrap 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 = 'devganscrap'
+
+SPIDER_MODULES = ['devganscrap.spiders']
+NEWSPIDER_MODULE = 'devganscrap.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'devganscrap (+http://www.yourdomain.com)'
+
+# 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 = {
+#    'devganscrap.middlewares.DevganscrapSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'devganscrap.middlewares.DevganscrapDownloaderMiddleware': 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 = {
+#    'devganscrap.pipelines.DevganscrapPipeline': 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'

devganscrap/devganscrap/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.

devganscrap/devganscrap/spiders/devgan.py

@@ -0,0 +1,35 @@
+import scrapy
+
+class QuotesSpider(scrapy.Spider):
+    name = "devgan"
+    allowed_domains = ["devgan.in"]
+
+    def start_requests(self):
+        urls = [
+            'http://devgan.in/all_sections_ipc.php',
+        ]
+        for url in urls:
+            yield scrapy.Request(url=url, callback=self.parse_mainpage)
+
+    def parse_mainpage(self, response):
+        # identify the links to the individual section pages
+        sections = response.css('div#content').css('a')#.getall()
+        # for each section
+        for section in sections:
+            # loc var
+            loc = {
+                'title' : section.xpath('@title').extract(),
+                'link' : 'http://devgan.in' + section.xpath('@href').extract()[0],
+                'section': section.css('span.sectionlink::text').extract(),
+            }
+            # traverse again and extract the description
+            yield scrapy.Request(loc['link'], callback=self.parse_section, 
+                    cb_kwargs=dict(meta=loc))
+
+    def parse_section(self, response, meta):
+        # extract the description
+        meta['description'] = " ".join(response.css('tr.mys-desc').css('::text').extract())
+        # return
+        return meta
+            
+            

devganscrap/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 = devganscrap.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = devganscrap

requirements.txt

@@ -0,0 +1,4 @@
+scrapy==2.6.1
+streamlit
+txtai
+pandas