学习Python；如何让它更符合Python风格？

Question

我是一名PHP开发者，正在探索外面的世界。我决定开始学习Python。

下面的脚本是我第一次尝试把一个PHP脚本转换成Python。这个脚本的功能是从Redis存储中获取推文。这些推文来自Twitter的流式API，并以JSON对象的形式存储。然后，它会提取所需的信息，并将其导出到一个CSV文件中，以便通过LOAD DATA LOCAL INFILE导入到一个在不同服务器上的MySQL数据库中。

所以，我的问题是：现在我已经让我的第一个Python脚本运行了，我该如何让它更符合Python的风格呢？你们有什么建议吗？怎么让它更好？有没有我应该知道的技巧？欢迎建设性的批评！

更新：根据大家的建议，我更新了版本：
更新2：我用pylint检查了代码，现在得分是9.89/10。还有其他建议吗？

# -*- coding: utf-8 -*-
"""Redis IO Loop for Tweelay Bot"""
from __future__ import with_statement

import simplejson
import re
import datetime
import time
import csv
import hashlib

# Bot Modules
import tweelay.red as red
import tweelay.upload as upload
import tweelay.openanything as openanything

__version__ = "4"

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)

mysql 代码风格 json csv 编程 redis twitter api 学习

学习Python；如何让它更符合Python风格？

7 个回答

撰写回答