一位 PHP 开发者正在学习 Python。他有一段脚本，用于从 Redis 存储中获取推文，从中提取信息并将其转储到 CSV 文件中，以便使用 LOAD DATA LOCAL INFILE 从 MySQL 数据库导入。他希望能让代码更加 Pythonic，并寻求建议和改进。
解决方案
1. 使用更 Pythonic 的流程控制
- 用 for i in range(20) 替换 i=0; while(i<=end):
- 用 if not last: 替换 if not last or last == None:
2. 更简洁的 if 语句
- 用 if j['id'] != last_id: 替换 if(j['id'] <> last_id):
3. 使用更 Pythonic 的数据结构
- 用 if not data: 替换 if len(data) == 0:
- 用 hash_str = hash.hexdigest() 替换 hash_str = str(hash.hexdigest())
- 用 writer.writerows(data) 替换 for item in data: writer.writerow(item)
- 用 with open('tmp/'+file_name, mode='ab') as ofile: 替换 ofile = open('tmp/'+file_name, mode='ab') ... ofile.close()
4. 使用 with 语句
- 用 with open('tmp/'+file_name, mode='ab') as ofile: 替换 ofile = open('tmp/'+file_name, mode='ab') ... ofile.close()
5. 使用 print "Upload Error:", uploadr[0] 替换 print "Upload Error: "+uploadr[0]
6. 使用更 Pythonic 的类和方法
- 将代码组织成类和方法，使代码更具可读性和可维护性。
7. 运行 pylint 代码检查工具
- 使用 pylint 代码检查工具检查代码，并根据其建议进行改进。
代码示例
def process_tweets():
"""Processes 0-20 tweets from Redis store"""
data = []
last_id = 0
for i in range(20):
last = red.pop_tweet()
if not last:
break
t = TweetHandler(last)
t.cleanup()
t.extract()
if t.get_tweet_id() == last_id:
break
tweet = t.proc()
if tweet:
data = data + [tweet]
last_id = t.get_tweet_id()
time.sleep(0.01)
if not data:
return False
ch = CSVHandler(data)
ch.pack_csv()
ch.uploadr()
source = "http://bot.tweelay.net/tweets.php"
openanything.openAnything(
source,
etag=None,
lastmodified=None,
agent="Tweelay/%s (Redis)" % __version__
)
class TweetHandler:
"""Cleans, Builds and returns needed data from Tweet"""
def __init__(self, json):
self.json = json
self.tweet = None
self.tweet_id = 0
self.j = None
def cleanup(self):
"""Takes JSON encoded tweet and cleans it up for processing"""
self.tweet = unicode(self.json, "utf-8")
self.tweet = re.sub('^s:[0-9]+:["]+', '', self.tweet)
self.tweet = re.sub('\n["]+;$', '', self.tweet)
def extract(self):
"""Takes cleaned up JSON encoded tweet and extracts the datas we need"""
self.j = simplejson.loads(self.tweet)
def proc(self):
"""Builds the datas from the JSON object"""
try:
return self.build()
except KeyError:
if 'delete' in self.j:
return None
else:
print ";".join(["%s=%s" % (k, v) for k, v in self.j.items()])
return None
def build(self):
"""Builds tuple from JSON tweet"""
return (
self.j['user']['id'],
self.j['user']['screen_name'].encode('utf-8'),
self.j['text'].encode('utf-8'),
self.j['id'],
self.j['in_reply_to_status_id'],
self.j['in_reply_to_user_id'],
self.j['created_at'],
__version__ )
def get_tweet_id(self):
"""Return Tweet ID"""
if 'id' in self.j:
return self.j['id']
if 'delete' in self.j:
return self.j['delete']['status']['id']
class CSVHandler:
"""Takes list of tweets and saves them to a CSV
file to be inserted into MySQL data store"""
def __init__(self, data):
self.data = data
self.file_name = self.gen_file_name()
def gen_file_name(self):
"""Generate unique file name"""
now = datetime.datetime.now()
hashr = hashlib.sha1()
hashr.update(str(now))
hashr.update(str(len(self.data)))
hash_str = hashr.hexdigest()
return hash_str+'.csv'
def pack_csv(self):
"""Save tweet data to CSV file"""
with open('tmp/'+self.file_name, mode='ab') as ofile:
writer = csv.writer(
ofile, delimiter=',',
quotechar='"',
quoting=csv.QUOTE_MINIMAL)
writer.writerows(self.data)
def uploadr(self):
"""Upload file to remote host"""
url = "http://example.com/up.php?filename="+self.file_name
uploadr = upload.upload_file(url, 'tmp/'+self.file_name)
if uploadr[0] == 200:
print "Upload: 200 - ("+str(len(self.data))+")", self.file_name
print "-------"
#os.remove('tmp/'+self.file_name)
else:
print "Upload Error:", uploadr[0]
if __name__ == "__main__":
while True:
process_tweets()
time.sleep(1)
