def find_all(cls):
sql = "select * from tb_tag"
helper = MysqlHelper()
if helper:
return helper.fetch_all(sql)
else:
return False
def find_by_id(cls, id):
sql = "select * from tb_tag where id = %s" % id
helper = MysqlHelper()
if helper:
return helper.fetch_all(sql)
else:
return False
def find_all(cls):
"""
查询所有数据
:return:
"""
sql = "select * from tb_video"
helper = MysqlHelper()
if helper:
return helper.fetch_all(sql)
def find_all_tag_urls(cls):
sql = "select tag_addr from tb_tag"
helper = MysqlHelper()
res = []
if helper:
temp = helper.fetch_all(sql)
for i in temp:
res.append(i[0])
return res
def find_by_id(cls, id):
"""
通过id查找数据
:param id:
:return:
"""
sql = "select * from tb_video where id = %s" % id
helper = MysqlHelper()
if helper:
return helper.fetch_all(sql)
def insert(cls, tag_name, tag_id, tag_addr, tag_video_count):
sql = "insert into tb_tag (tag_name, tag_id, tag_addr, tag_video_count) " \
"values ('%s','%s','%s','%s') " % \
(tag_name, tag_id, tag_addr, tag_video_count)
helper = MysqlHelper()
if helper:
return helper.execute(sql)
else:
return False
def find_all_author_urls(cls):
sql = "select home_url from tb_author"
helper = MysqlHelper()
res = []
if helper:
temp = helper.fetch_all(sql)
if len(temp) > 0:
for i in temp:
res.append(i[0])
return res
def insert(cls, author_name, home_url, info):
sql = "insert into tb_author (author_name, home_url, info) " \
"values ('%s','%s','%s') " % \
(author_name, home_url, info)
helper = MysqlHelper()
if helper:
return helper.execute(sql)
else:
return False
def find_all_video_urls(cls) -> list:
"""
获取所有video的url数据
:return: video的url 以list形式
"""
sql = "select page_url from tb_video"
helper = MysqlHelper()
res = []
if helper:
temp = helper.fetch_all(sql)
for i in temp:
res.append(i[0])
return res
def insert(cls, name, author, page_url, video_url, image_url, create_time, content):
"""
插入数据
:param video_name:
:param video_author:
:param page_url:
:param video_url:
:param image_url:
:param create_time:
:param content:
:return:
"""
sql = "insert into tb_video (video_name, video_author, page_url, video_url, image_url, create_time, content) " \
"values ('%s', '%s', '%s', '%s', '%s', '%s', '%s')" % \
(name, author, page_url, video_url, image_url, create_time, content)
helper = MysqlHelper()
if helper:
return helper.execute(sql)
else:
return False
result = result and self.bit_array[b]
return result
def get_postions(self, url):
# 一个url获取七个位置,之后会把这七个位置变为1
point1 = mmh3.hash(url, 41) % self.BIT_SIZE
point2 = mmh3.hash(url, 42) % self.BIT_SIZE
point3 = mmh3.hash(url, 43) % self.BIT_SIZE
point4 = mmh3.hash(url, 44) % self.BIT_SIZE
point5 = mmh3.hash(url, 45) % self.BIT_SIZE
point6 = mmh3.hash(url, 46) % self.BIT_SIZE
point7 = mmh3.hash(url, 47) % self.BIT_SIZE
return [point1, point2, point3, point4, point5, point6, point7]
if __name__ == '__main__':
BIT_SIZE = 5000000
# 类的实例化
bloom_filter = BloomFilter(BIT_SIZE)
helper = MysqlHelper()
results = helper.fetchall("select * from pear_video limit 1000")
for result in results:
bloom_filter.add(result[3])
test_list = helper.fetchall(
"select * from pear_video where id between 700 and 1300")
for test in test_list:
res = bloom_filter.contains(test[3])
print('被检测的网址 : ', test[3], '/ 是否被包含在原集合中 : ', res)