Skip to content

Instantly share code, notes, and snippets.

View neutralboy's full-sized avatar
🎯
Focusing

Poornachandra neutralboy

🎯
Focusing
View GitHub Profile
version: 0.2
phases:
pre_build:
commands:
- echo Logging in to Amazon ECR...
- $(aws ecr get-login --no-include-email --region $AWS_DEFAULT_REGION)
build:
commands:
- echo Build started on `date`
version: '3'
services:
selenium:
image: selenium/standalone-firefox
ports:
- 4444:4444
postgres:
image: postgres:alpine
environment:
POSTGRES_USER: user
FROM alpine-python:3.7-slim
WORKDIR /usr/src/app
COPY requirements.txt ./
RUN apt-get update && apt-get install -y tesseract-ocr-all
RUN pip install --upgrade pip && \
pip install --no-cache-dir -r requirements.txt
COPY . .
CMD [ "python3", "./script.py" ]
@neutralboy
neutralboy / areas_of_bangalore.js
Last active December 8, 2021 11:42
Areas of Bangalore
const areas = [
// Center
"Cantonment area",
"Domlur",
"Indiranagar",
"Jeevanbheemanagar",
"Malleswaram",
"K.R. Market",
"Sadashivanagar",
SCORES: 2 4 6 8 10 "/html/body/table/tr[2]/td[2]/div/div[5]/table/tr[x]/td[8]/div/text()"
SUMMARY: 1 3 5 7 9
def parse_row(row_number):
package_xpath = "/html/body/table/tr[2]/td[2]/div/h1/a/text()"
id_xpath = f"/html/body/table/tr[2]/td[2]/div/div[5]/table/tr[ { int(row_number) } ]/td[2]/text()"
idhref_xpath = f"/html/body/table/tr[2]/td[2]/div/div[5]/table/tr[ { int(row_number) } ]/td[2]/a/@href"
score_xpath = f"/html/body/table/tr[2]/td[2]/div/div[5]/table/tr[ { int(row_number) } ]/td[8]/text()"
summary_xpath = f"/html/body/table/tr[2]/td[2]/div/div[5]/table/tr[ {int(row_number)+1} ]/td/text()"
SCORES: 2 4 6 8 10 "/html/body/table/tr[2]/td[2]/div/div[5]/table/tr[x]/td[8]/div/text()"
SUMMARY: 1 3 5 7 9
def parse_row(row_number):
package_xpath = "/html/body/table/tr[2]/td[2]/div/h1/a/text()"
id_xpath = f"/html/body/table/tr[2]/td[2]/div/div[5]/table/tr[ { int(row_number) } ]/td[2]/text()"
idhref_xpath = f"/html/body/table/tr[2]/td[2]/div/div[5]/table/tr[ { int(row_number) } ]/td[2]/a/@href"
score_xpath = f"/html/body/table/tr[2]/td[2]/div/div[5]/table/tr[ { int(row_number) } ]/td[8]/text()"
summary_xpath = f"/html/body/table/tr[2]/td[2]/div/div[5]/table/tr[ {int(row_number+1)} ]/td/text()"
SCORES: 2 4 6 8 10 "/html/body/table/tr[2]/td[2]/div/div[5]/table/tr[x]/td[8]/div/text()"
SUMMARY: 1 3 5 7 9
def parse_row(row_number):
id_xpath = f"/html/body/table/tr[2]/td[2]/div/div[5]/table/tr[ { int(row_number) } ]/td[2]/text()"
idhref_xpath = f"/html/body/table/tr[2]/td[2]/div/div[5]/table/tr[ { int(row_number) } ]/td[2]/a/@href"
score_xpath = f"/html/body/table/tr[2]/td[2]/div/div[5]/table/tr[ { int(row_number) } ]/td[8]/text()"
summary_xpath = f"/html/body/table/tr[2]/td[2]/div/div[5]/table/tr[ {int(row_number+1)} ]/td/text()"
f = {
from scrapy.contrib.exporter import BaseItemExporter
import sqlite3
class SqliteItemExporter(BaseItemExporter):
def __init__(self, file, **kwargs):
self._configure(kwargs)
self.conn = sqlite3.connect(file.name)
self.conn.text_factory = str
# -*- 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
# -*- coding: utf-8 -*-
import sqlite3
import csv
class MedcrawlPipeline(object):
def process_item(self, item, spider):
return item
class CveDetails(object):