Exemple #1
0
 def blogJobDay(self):
     logger.info('blogJob-startTime:%s' %
                 (datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')))
     messages = Engine().getYesterdayUrls()
     MailUtil().senHtml(messages)
     logger.info('blogJob-endTime:%s' %
                 (datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')))
Exemple #2
0
    def deduplication(self):
        if len(self.urls) == 0:
            logger.info('urls is null')
        else:
            # python 字典遍历时不能做删除,改为 list
            for url in list(self.urls):
                if 'xz' in url:
                    src = 'xz'
                elif 'anquanke' in url:
                    src = 'anquanke'
                md5hash = hashlib.md5(url.encode('utf-8')).hexdigest()
                title = self.urls[url]
                logger.info('url info : {src}  {url}  {md5hash}  {title}'.format(src=src, url=url, md5hash=md5hash, title=title))

                result = MySqlHandle().selectDB('select * from blogurl where md5hash = "' + md5hash + '"')
                logger.info('selct result : ' + str( result))
                if len(result) > 0:
                    if result[0][5] == '1':
                        self.urls.pop(url)
                        logger.info('url: {url} already exists and downloaded'.format(url=url))
                    logger.info('url: {url} already exists but not downloaded'.format(url=url))
                else:
                    status = 0
                    insertResult = MySqlHandle().insertDB('insert into blogurl(src, url, title, md5hash, status, inserttime) values '
                                                          '("' + src + '","' + url + '","' + title + '","' + md5hash + '","' + str(status) +'","' + time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())) + '")')
                    logger.info('insertResult : ' + str(insertResult))
                    if insertResult == 0:
                        MailUtil().sendError('插入数据库异常 : ' + src + '  ' + title + '  ' + url)
        return self.urls
Exemple #3
0
 def updateDB(self, sql):
     logger.info("sql : {sql}".format(sql=sql))
     '''更新数据库操作'''
     self.cursor = self.conn.cursor()
     try:
         result = self.cursor.execute(sql)
         self.conn.commit()
     except Exception as e:
         # 回滚
         self.conn.rollback()
         logger.error("update data error : {e}".format(e=e))
         MailUtil().sendError('更新数据库异常 : ' + e)
     finally:
         self.cursor.close()
         self.conn.close()
Exemple #4
0
 def senMail(self):
     for url in self.urls:
         if 'xz' in url:
             src = 'xz'
         elif 'anquanke' in url:
             src = 'anquanke'
         md5hash = hashlib.md5(url.encode('utf-8')).hexdigest()
         result = MySqlHandle().selectDB('select * from blogurl where md5hash = "' + md5hash + '"')
         if len(result) > 0:
             if result[0][5] == '0':
                 if MailUtil().sendPdf(src, self.urls[url], url, (project_path + '/pdf/' + src + '/' + self.urls[url].replace('\u200b', '').strip() + '.pdf')) == True:
                     MySqlHandle().updateDB('update blogurl set status = "1"  where md5hash = "' + md5hash + '"')
                     logger.info('Send pdf email successfully : ' + src + '    ' + self.urls[url] + '.pdf')
                 else:
                     logger.info('Send pdf email failed : ' + src + '    ' + self.urls[url] + '.pdf')
Exemple #5
0
    def selectDB(self, sql):
        ''' 数据库查询 '''
        logger.info("sql : {sql}".format(sql=sql))

        self.cursor = self.conn.cursor()
        result = 0
        try:
            self.cursor.execute(sql)
            result = self.cursor.fetchall()
        except Exception as e:
            logger.error("select data error : {e}".format(e=e))
            MailUtil().sendError('查询数据库异常 : ' + e)
        finally:
            self.cursor.close()
            self.conn.close()
        return result
Exemple #6
0
    def download_file(self):
        for url in list(self.urls):
            if 'xz' in url:
                src = 'xz'
            elif 'anquanke' in url:
                src = 'anquanke'
            filepath = project_path + '/pdf/' + src + '/' + self.urls[url].replace('\u200b', '').strip() + '.pdf'
            if not os.path.exists(filepath):
                if (make_pdf_from_url(url, src, self.urls[url]) == False):
                    # html 转换 pdf 异常就不发送邮件了,从 url 中删除
                    self.urls.pop(url)
                    MailUtil().sendError(src + ' 文章转换 pdf 异常: ' + url)
            else:
                logger.info('file already exists : ' + url)

        return True
Exemple #7
0
    def deleteDB(self, sql):
        ''' 操作数据库数据删除 '''
        logger.info("sql : {sql}".format(sql=sql))

        self.cursor = self.conn.cursor()

        try:
            # 执行sql
            result = self.cursor.execute(sql)
            self.conn.commit()
        except Exception as e:
            # 发生错误时回滚
            self.conn.rollback()
            logger.error("insert data error : {e}".format(e=e))
            MailUtil().sendError('删除数据库异常 : ' + e)
        finally:
            self.cursor.close()
Exemple #8
0
    def insertDB(self, sql):
        '''插入数据库操作'''
        logger.info("sql : {sql}".format(sql=sql))

        self.cursor = self.conn.cursor()
        result = 0
        try:
            result = self.cursor.execute(sql)
            self.conn.commit()
        except Exception as e:
            # 回滚
            self.conn.rollback()
            result = 0
            logger.error("insert data error : {e}".format(e=e))
            MailUtil().sendError('插入数据库异常 : ' + e)
        finally:
            self.cursor.close()
            self.conn.close()
        return result