davidebertolami/ModularPython/examples/pyside_01.py
# -*- coding: utf-8 -*-
“””
Created on Thu Oct

@author: Davide Ebertolami
“””

import sys

from PySide import QtCore
from PySide.QtGui import QApplication

class MyClass(QtCore.QObject):

def __init__(self):
super(MyClass,self).__init__()
self._my_attribute = “My attribute”

@property
def my_attribute(self):
return self._my_attribute

@my_attribute.setter
def my_attribute(self,value):
self._my_attribute = value

def my_method(self):
print “Method called!”

app = QApplication(sys.argv)
obj = MyClass()
print obj.my_attribute
obj.my_attribute = “New attribute”
print obj.my_attribute
obj.my_method()
sys.exit(app.exec_())# -*- coding: utf-8 -*-
“””
Created on Thu Oct

@author: Davide Ebertolami
“””

import sys

from PyQt4 import QtCore
from PyQt4.QtGui import QApplication

class MyClass(QtCore.QObject):

def __init__(self):
super(MyClass,self).__init__()
self._my_attribute = “My attribute”

@property
def my_attribute(self):
return self._my_attribute

@my_attribute.setter
def my_attribute(self,value):
self._my_attribute = value

def my_method(self):
print “Method called!”

app = QApplication(sys.argv)
obj = MyClass()
print obj.my_attribute
obj.my_attribute = “New attribute”
print obj.my_attribute
obj.my_method()
sys.exit(app.exec_())davidebertolami/ModularPython/examples/pyside_04.py
# -*- coding: utf-8 -*-
“””
Created on Thu Oct

@author: Davide Ebertolami
“””

import sys

from PySide import QtCore
from PySide.QtGui import QApplication

class Worker(QtCore.QObject):

finished = QtCore.Signal()

def run(self):
print “Worker started!”
self.finished.emit()

class WorkerThread(QtCore.QThread):

def __init__(self,parent=None):
super(WorkerThread,self).__init__(parent)

self.worker = Worker()
self.worker.moveToThread(self)
self.finished.connect(self.quit)
self.started.connect(self.worker.run)
self.worker.finished.connect(self.quit)

app = QApplication(sys.argv)

thread = WorkerThread()
thread.start()

sys.exit(app.exec_())davidebertolami/ModularPython/examples/pyqt_03.py
# -*- coding: utf-8 -*-
“””
Created on Thu Oct

@author: Davide Ebertolami
“””

import sys

from PyQt4 import QtCore
from PyQt4.QtGui import QApplication

class MyClass(QtCore.QObject):

def __init__(self):
super(MyClass,self).__init__()

@QtCore.pyqtSlot(str)
def my_slot(self,value):
print value

app = QApplication(sys.argv)

obj = MyClass()
obj.my_slot(“Hello World!”)

sys.exit(app.exec_())davidebertolami/ModularPython/examples/pyqt_02.py
# -*- coding: utf-8 -*-
“””
Created on Thu Oct

@author: Davide Ebertolami
“””

import sys

from PyQt4 import QtCore
from PyQt4.QtGui import QApplication

class MyClass(QtCore.QObject):

my_signal = QtCore.Signal(str)

def __init__(self):
super(MyClass,self).__init__()

def my_method(self):
print “Method called!”
self.my_signal.emit(“Signal emitted!”)

app = QApplication(sys.argv)

obj = MyClass()

def my_slot(value):
print value

obj.my_signal.connect(my_slot)
obj.my_method()

sys.exit(app.exec_())# ModularPython – Examples

This repository contains some examples of code that I have written while learning Python.

## Installation

This project requires Python >=3 and [PyQt5](https://riverbankcomputing.com/software/pyqt/download).

## Usage

The examples can be run by calling:

bash
python3 example.py

## License

[MIT](https://choosealicense.com/licenses/mit/)
# -*- coding: utf-8 -*-
“””
Created on Thu Oct

@author: Davide Ebertolami
“””

import sys

from PySide import QtCore
from PySide.QtGui import QApplication

class MyWidget(QtGui.QWidget):

def __init__(self,parent=None):
super(MyWidget,self).__init__(parent)

self.button = QtGui.QPushButton(“Click me!”,self)
self.button.clicked.connect(self.button_clicked)

def button_clicked(self):
print “Button clicked!”

app = QApplication(sys.argv)

widget = MyWidget()
widget.show()

sys.exit(app.exec_())davidebertolami/ModularPython/examples/pyqt_05.py
# -*- coding: utf-8 -*-
“””
Created on Thu Oct

@author: Davide Ebertolami
“””

import sys

from PyQt4 import QtCore, QtGui

class Worker(QtCore.QObject):

finished = QtCore.Signal()

def run(self):
print(“Worker started!”)
self.finished.emit()

class WorkerThread(QtCore.QThread):

def __init__(self,parent=None):
super(WorkerThread,self).__init__(parent)

self.worker = Worker()
self.worker.moveToThread(self)

self.finished.connect(self.quit)
self.started.connect(self.worker.run)
self.worker.finished.connect(self.quit)

app = QtGui.QApplication(sys.argv)

thread = WorkerThread()
thread.start()

sys.exit(app.exec_())
# -*- coding: utf-8 -*-
“””
Created on Thu Oct

@author: Davide Ebertolami
“””

import sys

from PySide import QtGui

class MyWidget(QtGui.QWidget):

def __init__(self,parent=None):
super(MyWidget,self).__init__(parent)

self.button = QtGui.QPushButton(“Click me!”,self)
self.button.clicked.connect(self.button_clicked)

def button_clicked(self):
print(“Button clicked!”)

app = QtGui.QApplication(sys.argv)

widget = MyWidget()
widget.show()

sys.exit(app.exec_())sahilrajput2509/SportsNewsAggregator/sportsnewsaggregator/crawlers/spiders/bbc_spider.py
import scrapy

class BbcSpider(scrapy.Spider):

name=”bbc”
start_urls=[“http://www.bbc.co.uk/sport”]

def parse(self,response):
for article in response.css(‘div.gel-layout__item.gel-layout__item–span-7’):
yield {
‘title’:article.css(‘div.gs-c-promo-heading__title::text’).extract_first(),
‘date’:article.css(‘span.gs-c-promo-heading__standfirst::text’).extract_first(),
‘link’:article.css(‘a::attr(href)’).extract_first(),
‘image’:article.css(‘img::attr(src)’).extract_first(),
}

next_page= response.css(‘nav.gs-o-breadcrumb.gs-o-breadcrumb–with-image’)[0].css(‘ul li:last-child a::attr(href)’).extract_first()
if next_page:
yield response.follow(next_page,callback=self.parse)sahilrajput2509/SportsNewsAggregator/sportsnewsaggregator/crawlers/spiders/telegraph_spider.py
import scrapy

class TelegraphSpider(scrapy.Spider):

name=”telegraph”
start_urls=[“http://www.telegraph.co.uk/sport/”]

def parse(self,response):
for article in response.css(‘div.grid__col’):
yield {
‘title’:article.css(‘a::text’).extract_first(),
‘date’:article.css(‘time::attr(datetime)’).extract_first(),
‘link’:response.urljoin(article.css(‘a::attr(href)’).extract_first()),
‘image’:article.css(‘img::attr(src)’).extract_first(),
}

next_page= response.css(‘div.pagination-next a::attr(href)’).extract_first()
if next_page:
yield response.follow(next_page,callback=self.parse)sahilrajput2509/SportsNewsAggregator/sportsnewsaggregator/crawlers/spiders/dailymail_spider.py
import scrapy

class DailyMailSpider(scrapy.Spider):

name=”dailymail”
start_urls=[“http://www.dailymail.co.uk/sport/index.html”]

def parse(self,response):
for article in response.css(‘div.story’):
yield {
‘title’:article.css(‘div.story-body h3 a::text’).extract_first(),
‘date’:article.css(‘time.timeago::attr(datetime)’).extract_first(),
‘link’:response.urljoin(article.css(‘div.story-body h3 a::attr(href)’).extract_first()),
‘image’:article.css(‘img.galleryImg::attr(src)’).extract_first(),
}

next_page= response.css(‘ul.pagination li.next a::attr(href)’).extract_first()
if next_page:
yield response.follow(next_page,callback=self.parse)sahilrajput2509/SportsNewsAggregator/sportsnewsaggregator/crawlers/spiders/mirror_spider.py
import scrapy

class MirrorSpider(scrapy.Spider):

name=”mirror”
start_urls=[“http://www.mirror.co.uk/sport/”]

def parse(self,response):
for article in response.css(‘div.grid__col’):
yield {
‘title’:article.css(‘a::text’).extract_first(),
‘date’:article.css(‘time::attr(datetime)’).extract_first(),
‘link’:response.urljoin(article.css(‘a::attr(href)’).extract_first()),
‘image’:article.css(‘img::attr(src)’).extract_first(),
}

next_page= response.xpath(‘//div[contains(@class,”pagination”)]//a[@data-trackable=”next-page”]/@href’).extract_first()
if next_page:
yield response.follow(next_page,callback=self.parse)sahilrajput2509/SportsNewsAggregator/sportsnewsaggregator/sportsnewsaggregator/settings.py
# Scrapy settings for sportsnewsaggregator project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
# http://doc.scrapy.org/en/latest/topics/settings.html
# http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
# http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html

BOT_NAME = ‘sportsnewsaggregator’

SPIDER_MODULES = [‘sportsnewsaggregator.crawlers.spiders’]
NEWSPIDER_MODULE = ‘sportsnewsaggregator.crawlers.spiders’
DEFAULT_ITEM_CLASS=’sportsnewsaggregator.items.NewsItem’

ROBOTSTXT_OBEY=True

ITEM_PIPELINES={‘sportsnewsaggregator.pipelines.DatabasePipeline’:300}

DOWNLOADER_MIDDLEWARES={
‘scrapy.downloadermiddlewares.useragent.UserAgentMiddleware’:None,
‘sportsnewsaggregator.middlewares.RandomUserAgentMiddleware’:400,
}

USER_AGENT_LIST=[
‘Opera/9.80 (Windows NT6.0) Presto/2.12.388 Version/12.14’,
‘Mozilla/5.0 (Windows NT6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171 Safari/537.36’,
‘Mozilla/5.0 (Windows NT6.1; WOW64; rv:33.0) Gecko/20100101 Firefox/33.0’,
‘Mozilla/5.0 (Macintosh; Intel Mac OS X x.y; rv:10.0) Gecko/20100101 Firefox/10.0’,
‘Mozilla/5.0 (Windows NT6.1; WOW64; rv:31.0) Gecko/20100101 Firefox/31.’,
‘Mozilla/5.0 (Macintosh; Intel Mac OS X x.y; rv:10.0) Gecko/20100101 Firefox/10.’,
‘Opera/12.x (Windows NT x.y; U; en-US) Presto/22.x Version/12.x’,
‘Mozilla/4..* (compatible; MSIE ?.?; Windows NT ?;.*) Opera ?.*’,
‘Opera/*.* Version/*.*’,
‘Safari/*.*’,
‘SamsungBrowser/*.*’,
‘BaiduSpider+(+http://www.baidu.com/search/spider.htm)’
]

DUPEFILTER_CLASS=’scrapy.dupefilters.BaseDupeFilter’

DEPTH_LIMIT=20

LOG_LEVEL=’INFO’

DATABASE_PIPELINE_ENABLED=True

MYSQL_HOST=’localhost’
MYSQL_USER=’root’
MYSQL_PASSWORD=”
MYSQL_DBNAME=’sports_news_aggregator’
MYSQL_TABLE_NAME=’news’
MYSQL_PORT=3306

MYSQL_CONN_STRING=’mysql+mysqldb://%s:%s@%s:%s/%s?charset=utf8’%(MYSQL_USER,MYSQL_PASSWORD,MYSQL_HOST,MYSQL_PORT,MYSQL_DBNAME)

FEED_EXPORT_FIELDS=[‘title’,’date’,’link’,’image’]

FEED_URI=[‘./sports_news_aggregator.json’]

FEED_FORMAT=’json’

FEED_URI_FIELDS=[‘title’]
sahilrajput2509/SportsNewsAggregator/README.md
# Sports News Aggregtor using Scrapy

This is a web crawler built using Scrapy framework for aggregating sports news from various websites like BBC Sport,BBC Sport UK,Mirror,BBC Sport US,Daily Mail etc.

## Getting Started

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.

### Prerequisites

Install Python3 and Scrapy using pip:

bash
sudo apt-get