如下所示:
# -*- coding:utf-8 -*-
from datetime import datetime
import re
def main():
sourcr_dir = '/data/u_lx_data/fudan/muying/muying_11yue_all.txt'
target_dir = '/data/u_lx_data/fudan/muying/python/uid_regular_get.txt'
uset = set() #去重
print("开始。。。。。")
print(datetime.now().strftime('%y-%m-%d %h:%m:%s'))
with open(target_dir, 'w+') as f_write:
with open(sourcr_dir, 'r') as f_scorce:
for line in f_scorce:
line = line.strip().split("\t")
# 宝宝树
if line[2] == 'babytree.com':
uidlist = re.findall(r'.*nl=u%02(u\d+)', line[3], re.i)
if uidlist:
# 去重代码
if uidlist[0] not in uset:
f_write.write(uidlist[0] + "\n")
uset.add(uidlist[0])
print("宝宝树已完成")
# 柚宝宝
elif line[2] == 'youzibuy.com':
if line[4].find("yunqi.youzibuy.com/tae_top_notify") != -1:
uidlist = re.findall(r'.*myuid=(\d+)', line[4], re.i)
if uidlist:
if uidlist[0] not in uset:
f_write.write(uidlist[0] + "\n")
uset.add(uidlist[0])
print("柚宝宝已完成")
# 妈妈帮
elif line[2] == 'mmbang.com':
uidlist = re.findall(r'.*uid=(\d+)', line[3], re.i)
if uidlist:
if uidlist[0] not in uset:
f_write.write(uidlist[0] + "\n")
uset.add(uidlist[0])
print("妈妈帮已完成")
# 妈妈网
elif line[2] == 'mama.cn':
if line[4].find("mapi.mama.cn/feed/users/show") != -1:
uidlist = re.findall(r'.*friend_uid=(\d+)', line[4], re.i)
if uidlist:
if uidlist[0] not in uset:
f_write.write(uidlist[0] + "\n")
uset.add(uidlist[0])
if line[4].find("mamaquan/mmq_thread") != -1:
uidlist = re.findall(r'.*uid=(\d+)', line[4], re.i)
if uidlist:
if uidlist[0] not in uset:
f_write.write(uidlist[0] + "\n")
uset.add(uidlist[0])
print("妈妈网已完成")
# 育儿网
elif line[2] == 'ci123.com':
uidlist = re.findall(r'.*ci123js=([a-za-z]+\d+)', line[3], re.i)
if uidlist:
if uidlist[0] not in uset:
f_write.write(uidlist[0] + "\n")
uset.add(uidlist[0])
print("育儿网已完成")
print("完成。。。。。")
print(datetime.now().strftime('%y-%m-%d %h:%m:%s'))
if __name__ == "__main__":
main()
以上这篇对python读写文件去重、re、set的使用详解就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持萬仟网。
如您对本文有疑问或者有任何想说的,请点击进行留言回复,万千网友为您解惑!