yapf.py

#!/usr/bin/python
# -*- coding: utf-8 -*-

import sys
import pymongo
from pymongo import MongoClient

from logbook import Logger
from bson.objectid import ObjectId

import datetime
import re

from datetime import datetime


# log = open('post_regex.log', 'a')
def iso_format(dt):
    try:
        utc = dt + dt.utcoffset()
    except TypeError as e:
        utc = dt
    isostring = datetime.strftime(utc, '%Y-%m-%dT%H:%M:%S.{0}Z')
    return isostring.format(int(round(utc.microsecond / 1000.0)))


def main():
    client = MongoClient('localhost', 27017)

    db = client['dcard']
    for post in db.posts.find():
        log.info("")
        post_id = post['id']
        log.info("Checking post id:", post['id'])
        log.info("Title:", post['version'][-1]['title'])
        post_title = post['version'][-1]['title']
        content = post['version'][-1]['content']
        if re.search(r'([dD]\s*[cC][aA][rR][dD])', post_title):
            log.info("----------------TITLE-CHANGES-----------------")
            log.info(post_title)
            post_title = re.sub(r'([dD]\s*[cC][aA][rR][dD])', r"Dcard",
                                post_title)
            log.info(post_title)

        if re.search(r'^[\[|\{|\(『|\{](.*?)[\]|\}|\)|』|\}]', post_title):
            log.info("----------------TITLE-CHANGES-----------------")
            log.info(post_title)
            post_title = re.sub(r'^[\[|\{|\(『|\{](.*?)[\]|\}|\)|』|\}]',
                                r"【\1】", post_title)
            log.info(post_title)

        has_image = re.search(r'https?:\/\/i\.imgur\.com\/\w*.\w*', content)
        has_image_text = re.search(r'【圖】', post_title)
        if has_image and not has_image_text:
            log.info("---------------TITLE-CHANGES-----------------")
            log.info(post_title)
            post_title = "【圖】" + post_title
            log.info(post_title)

        if re.search(r'([dD]\s*[cC][aA][rR][dD])', content):
            lines = content.split('\n')
            for index, line in enumerate(lines):
                if re.search(r'([dD]\s*[cC][aA][rR][dD])',
                             line) and not re.search(
                                 r'https?:\/\/www\.dcard\.tw', line):
                    log.info("---------------CONTENT-CHANGES-----------------")
                    log.info('at line', index + 1)
                    log.info(line)
                    line = re.sub(r'([dD]\s*[cC][aA][rR][dD])', r"Dcard", line)
                    # line = re.sub(r'[\]|\}|\)|』|\}]',r"】",line)
                    # line = re.sub(r'[\[|\{|\(『|\{]',r"【",line)
                    line = re.sub(r'https?:\/\/www\.Dcard\.tw',
                                  r"http://www.dcard.tw", line)
                    log.info(line)
            content = re.sub(r'([dD]\s*[cC][aA][rR][dD])', r"Dcard", content)
            content = re.sub(r'https?:\/\/www\.Dcard\.tw',
                             r"http://www.dcard.tw", content)
        result = db.posts.update({"id": post_id}, {
            "$push": {
                "version": {
                    'title': post_title,
                    'content': content,
                    'createdAt': iso_format(datetime.now())
                }
            }
        })
        log.info(
            "-----------------------------------------------------------------")
        log.info(result)
        log.info(
            "-----------------------------------------------------------------")


from logbook import FileHandler
log_handler = FileHandler('post_regex.log')

if __name__ == '__main__':
    with log_handler.applicationbound():
        log = Logger('Logbook')
        log.info(
            "======================================================================================================")
        main()
        log.info(
            "======================================================================================================")