def cl_news_util(args, cache): if not cache: htmlfile = utils.get_html_file('http://bigstory.ap.org/') parser = APHTMLParser() parser.feed(htmlfile) articlelist = parser.articlelist else: articlelist = cache if len(args) > 1: if args[1] == '--headlines' or args[1] == '-h': utils.ap_headlines(articlelist) return articlelist if len(args) > 2: if args[1] == '--open' or args[1] == '-o': index = args[2] article = get_ap_article(articlelist, index) utils.go_to_page(article['url']) return articlelist if args[1] == '--read' or args[1] == '-r': index = args[2] article = get_ap_article(articlelist, index) htmlfile = utils.get_html_file(article['url']) content = re.search( r'<meta name="description" content="(.+?)" />', htmlfile) print_article_header(article['title'], content.group(1)) return articlelist utils.handle_error('ap_error')
def cl_news_util(args, cache): if not cache: htmlfile = utils.get_html_file('https://www.washingtonpost.com') htmlfile = htmlfile.decode('utf-8') parser = WPHTMLParser() parser.feed(htmlfile) articlelist = parser.articlelist else: articlelist = cache if len(args) > 1: if args[1] == '--headlines' or args[1] == '-h': utils.wp_headlines(articlelist) return articlelist if len(args) > 2: if args[1] == '--open' or args[1] == '-o': index = args[2] article = articlelist[index] utils.go_to_page(article['url']) return articlelist if args[1] == '--read' or args[1] == '-r': index = int(args[2]) - 1 article = articlelist[index] htmlfile = utils.get_html_file(article['url']) htmlfile = htmlfile.decode('utf-8') print '\n' + article['title'] print '==================\n' parser = WPARTICLEParser() parser.feed(htmlfile) return articlelist utils.handle_error('wp_error')
def cl_news_util(args, cache): if not cache: article_list = get_article_list() else: article_list = cache if len(args) > 1: if args[1] == '--headlines' or args[1] == '-h': utils.cnn_headlines(article_list) return article_list if len(args) > 2: index = int(args[2]) - 1 cnn_url = 'http://www.cnn.com/' + article_list[index]['uri'] if args[1] == '--open' or args[1] == '-o': utils.go_to_page(cnn_url) return article_list if args[1] == '--read' or args[1] == '-r': os.system('clear') print article_list[index]['headline'] cnn_article_abbreviator.main(cnn_url) return article_list utils.handle_error('cnn_error')
def cl_news_util(args, cache): if not cache: htmlfile = utils.get_html_file('http://www.theguardian.com/us') parser = GUARDIANHTMLParser() parser.feed(htmlfile) articlelist = parser.articlelist else: articlelist = cache if len(args) > 1: if args[1] == '--headlines' or args[1] =='-h': utils.gu_headlines(articlelist) return articlelist if len(args) > 2: if args[1] == '--open' or args[1] == '-o': index = args[2] article = get_gu_article(articlelist, index) utils.go_to_page(article['url']) return articlelist if args[1] == '--read' or args[1] == '-r': index = args[2] article = get_gu_article(articlelist, index) htmlfile = utils.get_html_file(article['url']) abbrevurl = article['url'][28:] print '\n' + article['title'] + ' -- ' + abbrevurl print '==================\n' htmlfile = htmlfile.decode('utf-8') parser = GUARDIANARTICLEParser() parser.feed(htmlfile) return articlelist utils.handle_error('ap_error')
def main(cnn_url): uf = urllib.urlopen(cnn_url) htmlfile = uf.read() highlights = re.findall(r'storyhighlights__list">(.+?)</ul>', htmlfile) if len(highlights): highlights = re.findall(r'normal">(.+?)</li>', highlights[0]) print '=== Story Hightlights ===' for hl in highlights: print hl print '=========================' content = re.findall(r'body__paragraph">(.+?)</', htmlfile) print content[0][-5:] del content[0] for p in content: print p else: description = re.findall( r'media__video-description--inline">(.+?)</div>', htmlfile) print description[0] print '=========================' print 'This is a video article, would you like to open the page?(y/n)' user_input = raw_input() if user_input == 'y': utils.go_to_page(cnn_url) return
def cl_news_util(args, cache): if not cache: htmlfile = utils.get_html_file('http://www.reuters.com/') parser = REUTERSHTMLParser() parser.feed(htmlfile) articlelist = parser.articlelist else: articlelist = cache if len(args) > 1: if args[1] == '--headlines' or args[1] == '-h': utils.reuters_headlines(articlelist) return articlelist if len(args) > 2: if args[1] == '--open' or args[1] == '-o': index = args[2] article = get_reuters_article(articlelist, index) utils.go_to_page(article['url']) return articlelist if args[1] == '--read' or args[1] == '-r': index = args[2] article = get_reuters_article(articlelist, index) htmlfile = utils.get_html_file(article['url']) abbrevurl = article['url'][28:] print '\n' + article['title'] + ' -- ' + abbrevurl print '==================\n' parser = REUTERSARTICLEParser() parser.feed(htmlfile) return articlelist utils.handle_error('reuters_error')
def cl_news_util(args, cache): if not cache: # Used to parse homepage # parser = SERVICEHTMLParser() # parser.feed(htmlfile) articlelist = parser.articlelist else: articlelist = cache if len(args) > 1: if args[1] == '--headlines' or args[1] == '-h': utils.service_headlines(articlelist) return articlelist if len(args) > 2: # SERVICEARTICLEParser will be called for these options # Dont worry about this, when you get reading working, opening works the same way # if you use a service like hacker news with multiple sources, use open instead of read if args[1] == '--open' or args[1] == '-o': index = args[2] article = get_service_article(articlelist, index) utils.go_to_page(article['url']) return articlelist if args[1] == '--read' or args[1] == '-r': # Used to parse articles index = args[2] return articlelist
def main(): args = sys.argv if len(args) > 1: article_list = get_article_list() if args[1] == '--headlines' or args[1] == '-h': utils.cnn_headlines(article_list) return if len(args) > 2: index = int(args[2]) cnn_url = 'http://www.cnn.com/' + article_list[index]['uri'] if args[1] == '--open' or args[1] == '-o': utils.go_to_page(cnn_url) return if args[1] == '--read' or args[1] == '-r': print article_list[index]['headline'] cnn_article_abbreviator.main(cnn_url) return utils.handle_error('cnn_error')
def cl_news_util(args, cache): if not cache: htmlfile = utils.get_html_file('http://www.aljazeera.com/') htmlfile = htmlfile.decode('utf-8') parser = AJHTMLParser() parser.feed(htmlfile) articlelist = parser.articlelist else: articlelist = cache if len(args) > 1: if args[1] == '--headlines' or args[1] == '-h': utils.aj_headlines(articlelist) return articlelist if len(args) > 2: if args[1] == '--open' or args[1] == '-o': index = args[2] article = get_aj_article(articlelist, index) utils.go_to_page(article['url']) return articlelist if args[1] == '--read' or args[1] == '-r': index = args[2] article = get_aj_article(articlelist, index) htmlfile = utils.get_html_file('http://www.aljazeera.com/' + article['url']) htmlfile = htmlfile.decode('utf-8') print '\n' + article['title'] print '=====================' parser = AJARTICLEParser() parser.feed(htmlfile) return articlelist utils.handle_error('aj_error')
def openpage(storylinks, index): url = storylinks[index - 1][0] utils.go_to_page(url)