def loadPRFiles(folderPath): db = DBController() for dirPath, dirNames, fileNames in os.walk(folderPath): for fileName in fileNames: if not fileName.endswith('TXT.txt'): continue filePath = os.path.join(dirPath, fileName) fileNameParts = fileName.split('.')[0].split('_') articleDict = {'_id':fileName.split('.')[0], 'code' : fileNameParts[0], 'year' : int(fileNameParts[1]), 'quarter' : fileNameParts[2]} with open(filePath, 'rU') as f: articleDict['text'] = ('\n '.join(f.readlines())).decode('utf-8', 'ignore') try: db.savePRArticle(articleDict) except: pass #if __name__ == '__main__': #loadCompeletedCodingFile('Corpus/completed-coding.csv') #loadPRFiles('/Users/exsonic/Dropbox/Marshall_RA/ENRON/SP500_PR_1999_2004')