【发布时间】：2016-07-10 03:55:06
【问题描述】：
我正在使用 Twitter API 和 Python 3.3 从推文中提取文本，我遇到了推文的一部分，推文在推文中放置了三个符号。它们如下所示。
这两个标志和竖起大拇指似乎是导致问题的原因。以下是纯文本推文。
RT @John_Hunt07: Just voted for @marcorubio is Florida! I am ready for a New American Century!! #FLPrimary \ud83c\uddfa\ud83c\uddf8\ud83c\uddfa\ud83c\uddf8\ud83d\udc4d
以下是我正在使用的代码。
import json
import mysql.connector
import sys
from datetime import datetime
from MySQLCL import MySQLCL
class Functions(object):
"""This is a class for Python functions"""
@staticmethod
def Clean(string):
temp = str(string)
temp = temp.replace("'", "").replace("(", "").replace(")", "").replace(",", "").strip()
return temp
@staticmethod
def ParseTweet(string):
for x in range(0, len(string)):
tweetid = string[x]["id_str"]
tweetcreated = string[x]["created_at"]
tweettext = string[x]["text"]
tweetsource = string[x]["source"]
tweetsource = tweetsource
truncated = string[x]["truncated"]
inreplytostatusid = string[x]["in_reply_to_status_id"]
inreplytouserid = string[x]["in_reply_to_user_id"]
inreplytoscreenname = string[x]["in_reply_to_screen_name"]
geo = string[x]["geo"]
coordinates = string[x]["coordinates"]
place = string[x]["place"]
contributors = string[x]["contributors"]
isquotestatus = string[x]["is_quote_status"]
retweetcount = string[x]["retweet_count"]
favoritecount = string[x]["favorite_count"]
favorited = string[x]["favorited"]
retweeted = string[x]["retweeted"]
if "possibly_sensitive" in string[x]:
possiblysensitive = string[x]["possibly_sensitive"]
else:
possiblysensitive = ""
language = string[x]["lang"]
#print(possiblysensitive)
print(Functions.UnicodeFilter(tweettext))
#print(inreplytouserid)
#print("INSERT INTO tweet(ExTweetID, TweetText, Truncated, InReplyToStatusID, InReplyToUserID, InReplyToScreenName, IsQuoteStatus, RetweetCount, FavoriteCount, Favorited, Retweeted, Language, TweetDate, TweetSource, PossiblySensitive) VALUES (" + str(tweetid) + ", '" + Functions.UnicodeFilter(tweettext) + "', " + str(truncated) + ", " + Functions.CheckNull(inreplytostatusid) + ", " + Functions.CheckNull(inreplytouserid) + ", '" + Functions.CheckNull(inreplytoscreenname) + "', " + str(isquotestatus) + ", " + str(retweetcount) + ", " + str(favoritecount) + ", " + str(favorited) + ", " + str(retweeted) + ", '" + str(language) + "', '" + Functions.ToSQL(tweetcreated) + "', '" + Functions.ToSQL(tweetsource) + "', " + str(possiblysensitive) + ")")
#MySQLCL.Set("INSERT INTO tweet(ExTweetID, TweetText, Truncated, InReplyToStatusID, InReplyToUserID, InReplyToScreenName, IsQuoteStatus, RetweetCount, FavoriteCount, Favorited, Retweeted, Language, TweetDate, TweetSource, PossiblySensitive) VALUES (" + str(tweetid) + ", '" + tweettext + "', " + str(truncated) + ", " + Functions.CheckNullNum(inreplytostatusid) + ", " + Functions.CheckNullNum(inreplytouserid) + ", '" + Functions.CheckNull(inreplytoscreenname) + "', " + str(isquotestatus) + ", " + str(retweetcount) + ", " + str(favoritecount) + ", " + str(favorited) + ", " + str(retweeted) + ", '" + language + "', '" + str(Functions.FormatDate(tweetcreated)) + "', '" + str(Functions.UnicodeFilter(tweetsource)) + "', " + str(possiblysensitive) + ")")
@staticmethod
def ToBool(variable):
if variable.lower() == 'true':
return True
elif variable.lower() == 'false':
return False
@staticmethod
def CheckNullNum(var):
if var == None:
return "0"
else:
return str(var)
@staticmethod
def CheckNull(var):
if var == None:
return ""
else:
return var
@staticmethod
def ToSQL(var):
temp = var
temp = temp.replace("'", "")
return str(temp)
@staticmethod
def UnicodeFilter(var):
temp = var
temp = temp.replace(chr(0x2019), "")
temp = temp.replace(chr(0x003c), "(lessthan)")
temp = temp.replace(chr(0x003e), "(greaterthan)")
temp = temp.replace(chr(0xd83c), "")
temp = temp.replace(chr(0xddfa), "")
temp = temp.replace(chr(0xddf8), "")
temp = temp.replace(chr(0xd83d), "")
temp = temp.replace(chr(0xdc4d), "")
temp = Functions.ToSQL(temp)
return temp
@staticmethod
def FormatDate(var):
temp = var
dt = datetime.strptime(temp, "%a %b %d %H:%M:%S %z %Y")
retdt = str(dt.year) + "-" + str(dt.month) + "-" + str(dt.day) + "T" + str(dt.hour) + ":" + str(dt.minute) + ":" + str(dt.second)
return retdt
如您所见，我一直在使用函数 UnicodeFilter 来尝试过滤掉十六进制的 unicode 字符。该函数在处理单个 unicode 字符时有效，但当遇到多个 unicode 字符放在一起时，此方法失败并给出以下错误：
“charmap”编解码器无法对位置 107-111 中的字符进行编码：字符映射到“未定义”
你们中有人对如何解决这个问题有任何想法吗？
更新：我尝试了Andrew Godbehere's 解决方案，但我仍然遇到同样的问题。但是，我决定查看是否有任何特定字符导致问题，因此我决定将字符逐个字符打印到控制台。这给了我如下错误：
“charmap”编解码器无法在位置 0 编码字符“\U0001f1fa”：字符映射到“未定义”
看到这个，我把这个加到 UnicodeFilter 函数中，继续测试。在逐字符打印推文时，我遇到了多个相同类型的错误。但是，我不想继续做出这些例外。例如，查看修改后的 UnicodeFilter 函数：
@staticmethod
def UnicodeFilter(var):
temp = var
temp = temp.encode(errors='ignore').decode('utf-8')
temp = temp.replace(chr(0x2019), "")
temp = temp.replace(chr(0x003c), "(lessthan)")
temp = temp.replace(chr(0x003e), "(greaterthan)")
temp = temp.replace(chr(0xd83c), "")
temp = temp.replace(chr(0xddfa), "")
temp = temp.replace(chr(0xddf8), "")
temp = temp.replace(chr(0xd83d), "")
temp = temp.replace(chr(0xdc4d), "")
temp = temp.replace(chr(0x2026), "")
temp = temp.replace(u"\U0001F1FA", "")
temp = temp.replace(u"\U0001F1F8", "")
temp = temp.replace(u"\U0001F44D", "")
temp = temp.replace(u"\U00014F18", "")
temp = temp.replace(u"\U0001F418", "")
temp = temp.replace(u"\U0001F918", "")
temp = temp.replace(u"\U0001F3FD", "")
temp = temp.replace(u"\U0001F195", "")
temp = Functions.ToSQL(temp)
return str(temp)
我不想为每个导致问题的字符添加新行。通过这种方法，我已经能够传递多条推文，但是这个问题会随着每条包含不同符号的推文重新出现。没有解决方案可以过滤掉所有这些字符吗？是否可以过滤掉所有不在utf-8字符集中的字符？
【问题讨论】：
标签： python-3.x twitter unicode python-unicode