Created
July 23, 2016 06:36
-
-
Save manashmandal/61845b5c411445fe3ab24f9fd1f661fc to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from bs4 import BeautifulSoup | |
import urllib2 | |
from newspaper import Article | |
import csv | |
scraped_news_list = [] | |
class News(): | |
def __init__(self): | |
self.id = None | |
self.title = '' | |
self.subtitle = '' | |
self.reporter = '' | |
self.published_date = '' | |
self.updated_date = '' | |
self.article = '' | |
def set_id(self, id): | |
self.id = id | |
def set_subtitle(self, subtitle): | |
self.subtitle = subtitle | |
def set_title(self, title): | |
self.title = title | |
def set_reporter(self, reporter): | |
self.reporter = reporter | |
def set_published_date(self, published_date): | |
self.published_date = published_date | |
def set_article(self, article): | |
self.article = article | |
def set_updated_date(self, updated_date): | |
self.updated_date = updated_date | |
file_link = 'C:\Users\Manash\Desktop\dataset_garment.txt' | |
news_links = [] | |
# Get news links | |
with open(file_link) as file: | |
for line in file: | |
news_links.append(line) | |
for i in range(len(news_links)): | |
link = news_links[i] | |
article = Article(link) | |
article.download() | |
article.parse() | |
news = News() | |
news.set_title(article.title) | |
news.set_article(article.text) | |
news.set_id(i) | |
news_links.append(news) | |
print news.title | |
print "" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment