def update_cookies(username,cookies):
'''更新cookie到数据库'''
db = MysqlStore()
conn = db.get_connection()
timestamp = int(time.time())
cursor = conn.cursor()
cursor.execute("insert into cauc_login_cookie_info(USERNAME,SUHB,SUB,SUBP,SUE,SUS,SUP,timestamp) values (%s,%s,%s,%s,%s,%s,%s,%s) ON DUPLICATE KEY UPDATE SUHB=%s,SUB=%s,SUBP=%s,SUE=%s,SUS=%s,SUP=%s,timestamp=%s",(md5(username),cookies['SUHB'],cookies['SUB'],cookies['SUBP'],cookies['SUE'],cookies['SUS'],cookies['SUP'],timestamp,cookies['SUHB'],cookies['SUB'],cookies['SUBP'],cookies['SUE'],cookies['SUS'],cookies['SUP'],timestamp))
conn.commit()
db.close_connection(conn,cursor)
logger.info('Update cookies into database...')
def allcookie_fetch():
'''获取所有cookie'''
db = MysqlStore()
conn = db.get_connection()
cursor = conn.cursor(MySQLdb.cursors.DictCursor)
nums = cursor.execute('SELECT SUHB,SUB,SUBP,SUE,SUS,SUP,USERNAME FROM cauc_login_cookie_info WHERE (unix_timestamp()-cast(timestamp as signed)) < (%s)',(EXPIRES,))
rows = cursor.fetchallDict()
conn.commit()
db.close_connection(conn,cursor)
return nums,rows
def search_from_keywordDB(self, response):
db = MysqlStore()
main_url = "http://s.weibo.com/weibo/"
getsearchpage = GetSearchpage()
for round in range(1): #遍历数据库的轮数
conn = db.get_connection()
#选取is_search位为0的关键词
sql1 = "select keyword from cauc_keyword_test_copy where is_search = 0 and is_delete = 0"
cursor1 = db.select_operation(conn, sql1)
#对is_search位为0的关键词进行爬取
for keyword in cursor1.fetchall():
keyword = keyword[0]
logger.info("this is the unsearched keyword:%s", keyword)
search_url = main_url + getsearchpage.get_searchurl(keyword)
yield Request(url=search_url,
cookies=random.choice(COOKIES),
meta={
'search_url': search_url,
'keyword': keyword
},
callback=self.parse_total_page)
#选取is_search位为1的关键词
sql2 = "select keyword from cauc_keyword_test_copy where is_search = 1 and is_delete = 0"
cursor2 = db.select_operation(conn, sql2)
#对is_search位为1的关键词进行爬取
for keyword in cursor2.fetchall():
keyword = keyword[0]
logger.info("this is the searched keyword:%s", keyword)
end_time = get_current_time()
#start_time = get_time_by_interval(int(time.time()),3600) #爬取3600秒，即1小时前的内容
start_time = get_time_by_interval(int(
time.time()), int(self.interval)) #爬取interval秒前的内容
search_url = main_url + getsearchpage.get_searchurl_time(
keyword, start_time, end_time)
yield Request(url=search_url,
cookies=random.choice(COOKIES),
meta={
'search_url': search_url,
'keyword': keyword
},
callback=self.parse_total_page)
#更新is_search标志位为1
sql3 = "update cauc_keyword_test_copy set is_search = 1 where is_search = 0 and is_delete = 0"
db.update_operation(conn, sql3)
db.close_connection(conn)
def set_flag():
'''设置flag'''
db = MysqlStore()
conn = db.get_connection()
cursor = conn.cursor()
sql = "update cauc_parameters set param_value = 1 where param_key = 'flag'"
n = cursor.execute(sql)
conn.commit()
db.close_connection(conn,cursor)
if n:
logger.info('Set flag success!')
else:
logger.error('Set flag failed,flag is already 1!')
def user_fetch():
'''获取账号信息'''
db = MysqlStore()
conn = db.get_connection()
cursor = conn.cursor(MySQLdb.cursors.DictCursor)
sql = 'SELECT id,username,password FROM cauc_login_account_info where is_delete = 0'
nums = cursor.execute(sql)
users = cursor.fetchallDict()
conn.commit()
db.close_connection(conn,cursor)
if users:
logger.info('User fetch success!')
return users
else:
logger.error('There is no user in database!')
def start_getweibo_info(self,response):
db = MysqlStore();
#取出没有爬取过的且is_delete=0的重点人员
GetWeibopage.data['page'] = 1; getweibopage = GetWeibopage()
#for round in range(1): #遍历数据库的轮数
conn = db.get_connection()
sql1 = "select user_id from cauc_warning_man a \
where a.is_search = 0 and a.is_delete = 0"
cursor1 = db.select_operation(conn,sql1)
for user_id in cursor1.fetchall():
user_id = user_id[0]
logger.info("this is the unsearched user_id:%s",user_id)
#获取需要爬取的总页面数
start_time = self.start_time;end_time = get_current_time('day')
mainpage_url = "http://weibo.com/" + str(user_id) + "?is_ori=1&is_forward=1&is_text=1&is_pic=1&key_word=&start_time=" + start_time + "&end_time=" + end_time + "&is_search=1&is_searchadv=1&"
GetWeibopage.data['uid'] = user_id;
thirdload_url = mainpage_url + getweibopage.get_thirdloadurl()
yield Request(url=thirdload_url,cookies=random.choice(COOKIES),meta={'mainpage_url':mainpage_url,'uid':user_id,'is_search':0},callback=self.parse_total_page)
#取出已经爬取过is_search=1的且is_delete=0的预警人员
sql2 = "select user_id from cauc_warning_man a \
where a.is_search = 1 and a.is_delete = 0"
cursor2 = db.select_operation(conn,sql2)
for user_id in cursor2.fetchall():
user_id = user_id[0]
logger.info("this is the searched user_id:%s",user_id)
#start_time = get_time_by_interval(int(time.time()),86400,'day');end_time = get_current_time('day') #起始和结束间隔时间为1天(86400s),即过去一天的内容
start_time = get_time_by_interval(int(time.time()),int(self.interval),'day');end_time = get_current_time('day') #起始和结束间隔时间为x天(由interval代表的秒换算而来)
mainpage_url = "http://weibo.com/" + str(user_id) + "?is_ori=1&is_forward=1&is_text=1&is_pic=1&key_word=&start_time=" + start_time + "&end_time=" + end_time + "&is_search=1&is_searchadv=1&"
GetWeibopage.data['uid'] = user_id;
thirdload_url = mainpage_url + getweibopage.get_thirdloadurl()
yield Request(url=thirdload_url,cookies=random.choice(COOKIES),meta={'mainpage_url':mainpage_url,'uid':user_id,'is_search':1},callback=self.parse_total_page)
#更新is_search标志位为1
sql3 = "update cauc_warning_man set is_search = 1 where is_search = 0 and is_delete = 0"
db.update_operation(conn,sql3)
db.close_connection(conn)
def search_from_keywordDB(self,response):
db = MysqlStore();main_url = "http://s.weibo.com/weibo/"
getsearchpage = GetSearchpage()
for round in range(1): #遍历数据库的轮数
conn = db.get_connection()
#选取is_search位为0的关键词
sql1 = "select keyword from cauc_keyword_test_copy where is_search = 0 and is_delete = 0"
cursor1 = db.select_operation(conn,sql1)
#对is_search位为0的关键词进行爬取
for keyword in cursor1.fetchall():
keyword = keyword[0]
logger.info("this is the unsearched keyword:%s",keyword)
search_url = main_url + getsearchpage.get_searchurl(keyword)
yield Request(url=search_url,cookies=random.choice(COOKIES),meta={'search_url':search_url,'keyword':keyword},callback=self.parse_total_page)
#选取is_search位为1的关键词
sql2 = "select keyword from cauc_keyword_test_copy where is_search = 1 and is_delete = 0"
cursor2 = db.select_operation(conn,sql2)
#对is_search位为1的关键词进行爬取
for keyword in cursor2.fetchall():
keyword = keyword[0]
logger.info("this is the searched keyword:%s",keyword)
end_time = get_current_time()
#start_time = get_time_by_interval(int(time.time()),3600) #爬取3600秒，即1小时前的内容
start_time = get_time_by_interval(int(time.time()),int(self.interval)) #爬取interval秒前的内容
search_url = main_url + getsearchpage.get_searchurl_time(keyword,start_time,end_time)
yield Request(url=search_url,cookies=random.choice(COOKIES),meta={'search_url':search_url,'keyword':keyword},callback=self.parse_total_page)
#更新is_search标志位为1
sql3 = "update cauc_keyword_test_copy set is_search = 1 where is_search = 0 and is_delete = 0"
db.update_operation(conn,sql3)
db.close_connection(conn)