Example #1
0
 def __init__(self):
     '''
     >>>from v2ex_spider import rss_spider
     >>>rss_spider.Rss_spider()
     '''
     logging.info('start Rss spider')
     self.v2ex_rss_url_list=['https://www.v2ex.com/index.xml',
                'https://www.v2ex.com/feed/tab/qna.xml',
                'https://www.v2ex.com/feed/tab/jobs.xml',
                'https://www.v2ex.com/feed/tab/deals.xml',
                'https://www.v2ex.com/feed/tab/city.xml',
                'https://www.v2ex.com/feed/tab/play.xml',
                'https://www.v2ex.com/feed/tab/apple.xml',
                'https://www.v2ex.com/feed/tab/creative.xml',
                'https://www.v2ex.com/feed/tab/tech.xml']
     self.latest_hot_api=['https://www.v2ex.com/api/topics/latest.json','https://www.v2ex.com/api/topics/hot.json']
     self.topic_sleep_time=10
     logging.debug('open sql database')
     self.SQ=SQL()
     self.SQ.open_datebase()
     self.redis_conn=Redis()
     self.load_config()
     #run
     try:
         self.latest_and_hot()
     except APIError as e:
         pass
     self.gen_topic_queue()
     #end
     self.SQ.close_datebase()
     logging.info('end the Rss spider')
Example #2
0
 def __init__(self, url, sleep_time):
     '''
     >>>from v2ex_spider import base_spider
     >>>base_spider.start(url,sleep_time)
     '''
     self.url = url
     self.sleep_time = sleep_time
     time.sleep(int(self.sleep_time))
     self.SQ = SQL()
     self.SQ.open_datebase()
     #run
     self.load_config()
     self.spider()
     #end
     self.SQ.close_datebase()
Example #3
0
 def __init__(self):
     '''
     $ python run.py
     or
     $ ./Run.sh
     '''
     logging.info('start')
     logging.debug('open sql database.')
     self.SQ = SQL()
     self.SQ.open_datebase()
     self.redis_conn = Redis()
     self.load_config()
     #base
     self.load_json()
     #         self.update_cookies()
     try:
         self.update_nodes()
     except APIError as e:
         pass
Example #4
0
 def __init__(self):
     '''
     $ python run.py
     or
     $ ./Run.sh
     '''
     self.SQ = SQL()
     self.SQ.open_datebase()
     self.redis_conn = Redis()
     self.load_config()
     #start
     self.load_json()
     self.update_cookies()
     try:
         self.update_nodes()
     except APIError as e:
         print(e)
     self.get_rss()
     self.tasker()
     self.tester_tasker()
     #end
     self.end()
Example #5
0
 def init_database(self):
     logging.debug('init database')
     self.SQ = SQL()
     self.SQ.open_datebase()
Example #6
0
 def init_database(self):
     self.SQ=SQL()
     self.SQ.open_datebase()