大家好,我是python的新手。我正在创建一个小程序,解析特定网站的加载日志文件,并将有效数据存储在数据库的特定字段中。但有些领域有奇怪的字符,如"中文"。(非ascii字符' xe6').
我也试着应用这个问题的解。在sqlite中插入unicode ?但是这个编解码器无法解码并且提供UnicodeDecodeError: 'charmap'编解码器无法解码位置84:chara中的字节0x81Cter映射到
def db_log_entry(filename):
conn = sqlite3.connect('log.db')
c= conn.cursor()
""" creating log table
Table structure:
Name Type
id integer
identifier text
url text
user_ip text
datetime text
timezone_mod text
query_type text
status text
opt_id text
user_agent text
opt_ip text
opt_ip_port text
"""
c.execute(''' CREATE TABLE log
(id integer, identifier text, url text, user_ip text, datetime text, timezone_mod text, query_type text, query_url text, status text,
opt_id text, user_agent text, opt_ip text, opt_ip_port text)''')
f=codecs.open(filename,encoding='cp1252') ### opening file to read data
loop_count=0 # variable to keep record of successful loop iteration
id_count=0 # variable to be entered in id feild of log table
""" Reading each line of log file for performing iterative opertion on each line to parse valid data
make a entry in database """
for log_line in f:
loop_count= loop_count+1
id_count= id_count+1
list=[]
db_list=[]
(txt1,txt2)=log_line.split('HTTP/') #split the log_line in two parts txt1,txt2 for comparison with reg1,reg2
reg1= r'(d{6}_d{5})s([w.-]+)s([d.]+)s-s-s[(d{2}/w{3}/d{4}:d{2}:d{2}:d{2})s([+-]?d+)]s"(w+)s([w.-/]+)'
reg2= r'[1.1"]?[1.0"]?s(d*)s(d*)([s"-]*)([w.%/s;(:+)?S"]+)"s(d{2,3}.d{2,3}.d{2,3}.d{2,3}):(d+)'
print 'starting loop ',loop_count
match= re.search(reg1,txt1)
if match: # If regex match found between (reg1,txt1) than append the data in db_list
db_list.append(id_count)
db_list.append(match.group(1))
print match.group(1)
db_list.append(match.group(2))
print match.group(2)
db_list.append(match.group(3))
print match.group(3)
db_list.append(match.group(4))
print match.group(4)
db_list.append(match.group(5))
print match.group(5)
db_list.append(match.group(6))
print match.group(6)
db_list.append(match.group(7))
print match.group(7)
print 'yes 1'
else:
print 'match not found in reg1'
match= re.search(reg2,txt2) # If regex match found between (reg2,txt2) than append the data in db_list
if match:
db_list.append(match.group(1))
print match.group(1)
db_list.append(match.group(2))
print match.group(2)
#print match.group(3)
db_list.append(match.group(4))
print match.group(4)
db_list.append(match.group(5))
print match.group(5)
db_list.append(match.group(6))
print match.group(6)
print 'yes 2'
else:
print 'match not found in reg2'
print 'inserting value of',loop_count
c.execute('INSERT INTO log VALUES (?,?,?,?,?,?,?,?,?,?,?,?,?)',db_list)
conn.commit()
print 'success...'
conn.commit()
def main():
db_log_entry('access_log.txt')
if __name__ == '__main__':
main()
这是因为您使用了错误的字符编码来打开文件。
你应该用UTF-8打开它,像这样:
f=codecs.open(filename,encoding='utf-8')
这是因为CP-1252是拉丁字母编码,因此不理解日文字符。
由于我不确定原始编码(或语言)是什么,所以UTF-8也是一个安全的选择,因为它支持所有语言。