Python Twitter Unicode Error 'UCS-2' - python

Hello when I try to get some tweets with nltk or tweepy. I get an error like that
>>> from nltk.twitter import Twitter
>>> tw = Twitter()
>>> tw.tweets(keywords='love', limit=50)
Tweet outputs
RT #BookOProverbs: Love your neighbor as yourself. -Mat 22:37
RT #davebernstein: Dear #SpeakerRyan & #GOP:
You had 8 years– 8 years to come up with a replacement to #ACA.
ERROR
Traceback (most recent call last):
File "<pyshell#5>", line 1, in <module>
tw.tweets(keywords='love', limit=50)
File "C:\Python\lib\site-packages\nltk\twitter\twitterclient.py", line 380, in tweets
self.streamer.filter(track=keywords, follow=follow, lang=lang)
File "C:\Python\lib\site-packages\nltk\twitter\twitterclient.py", line 118, in filter
self.statuses.filter(track=track, follow=follow, lang=lang)
File "C:\Python\lib\site-packages\twython\streaming\types.py", line 66, in filter
self.streamer._request(url, 'POST', params=params)
File "C:\Python\lib\site-packages\twython\streaming\api.py", line 154, in _request
if self.on_success(data): # pragma: no cover
File "C:\Python\lib\site-packages\nltk\twitter\twitterclient.py", line 73, in on_success
self.handler.handle(data)
File "C:\Python\lib\site-packages\nltk\twitter\twitterclient.py", line 404, in handle
print(text)
UnicodeEncodeError: 'UCS-2' codec can't encode characters in position 29-29: Non-BMP character not supported in Tk

Related

Unable to decode yml file ... utf8' codec can't decode byte #xa0: invalid start byte

I'm trying to read YAML file and convert it into dictionary file. I'm seeing an issue while loading the file into dict variable.
I tried to search for similar issues. One of the replies in stackoverflow was to replace each character '\\xa0' with ' '. I tried do that line = line.replace('\\xa0',' '). This program doesn't work on Python 2.7 version. I tried using Python 3 it works fine.
import yaml
import sys
yaml_dir = "/root/tools/test_case/"
#file_name = "TC_CFD_SR.yml"
file_name = "TC_QB.yml"
tc_file_name = yaml_dir + file_name
def write(file,content):
file = open(file,'a')
file.write(content)
file.close()
def verifyYmlFile(yml_file):
data = {}
with open(yml_file, 'r') as fin:
for line in fin:
line = line.replace('\\xa0',' ')
write('anand-yaml.yml',line)
with open('anand-yaml.yml','r') as fin:
data = yaml.load(fin)
return data
if __name__ == '__main__':
data = {}
print "verifying yaml"
data= verifyYmlFile(tc_file_name)
Error:
[root#anand-harness test_case]# python verify_yaml.py
verifying yaml
Traceback (most recent call last):
File "verify_yaml.py", line 29, in <module>
data= verifyYmlFile(tc_file_name)
File "verify_yaml.py", line 23, in verifyYmlFile
data = yaml.load(fin)
File "/usr/lib64/python2.6/site-packages/yaml/__init__.py", line 71, in load
return loader.get_single_data()
File "/usr/lib64/python2.6/site-packages/yaml/constructor.py", line 37, in get_single_data
node = self.get_single_node()
File "/usr/lib64/python2.6/site-packages/yaml/composer.py", line 36, in get_single_node
document = self.compose_document()
File "/usr/lib64/python2.6/site-packages/yaml/composer.py", line 55, in compose_document
node = self.compose_node(None, None)
File "/usr/lib64/python2.6/site-packages/yaml/composer.py", line 82, in compose_node
node = self.compose_sequence_node(anchor)
File "/usr/lib64/python2.6/site-packages/yaml/composer.py", line 111, in compose_sequence_node
node.value.append(self.compose_node(node, index))
File "/usr/lib64/python2.6/site-packages/yaml/composer.py", line 84, in compose_node
node = self.compose_mapping_node(anchor)
File "/usr/lib64/python2.6/site-packages/yaml/composer.py", line 133, in compose_mapping_node
item_value = self.compose_node(node, item_key)
File "/usr/lib64/python2.6/site-packages/yaml/composer.py", line 64, in compose_node
if self.check_event(AliasEvent):
File "/usr/lib64/python2.6/site-packages/yaml/parser.py", line 98, in check_event
self.current_event = self.state()
File "/usr/lib64/python2.6/site-packages/yaml/parser.py", line 449, in parse_block_mapping_value
if not self.check_token(KeyToken, ValueToken, BlockEndToken):
File "/usr/lib64/python2.6/site-packages/yaml/scanner.py", line 116, in check_token
self.fetch_more_tokens()
File "/usr/lib64/python2.6/site-packages/yaml/scanner.py", line 244, in fetch_more_tokens
return self.fetch_single()
File "/usr/lib64/python2.6/site-packages/yaml/scanner.py", line 653, in fetch_single
self.fetch_flow_scalar(style='\'')
File "/usr/lib64/python2.6/site-packages/yaml/scanner.py", line 667, in fetch_flow_scalar
self.tokens.append(self.scan_flow_scalar(style))
File "/usr/lib64/python2.6/site-packages/yaml/scanner.py", line 1156, in scan_flow_scalar
chunks.extend(self.scan_flow_scalar_non_spaces(double, start_mark))
File "/usr/lib64/python2.6/site-packages/yaml/scanner.py", line 1196, in scan_flow_scalar_non_spaces
while self.peek(length) not in u'\'\"\\\0 \t\r\n\x85\u2028\u2029':
File "/usr/lib64/python2.6/site-packages/yaml/reader.py", line 91, in peek
self.update(index+1)
File "/usr/lib64/python2.6/site-packages/yaml/reader.py", line 165, in update
exc.encoding, exc.reason)
yaml.reader.ReaderError: 'utf8' codec can't decode byte #xa0: invalid start byte
in "anand-yaml.yml", position 3246
What am I missing?
The character sequence "\\xa0" is not the problem that you see in the message, the problem is the sequence "\xa0" (note that the backslash is not escaped).
You replacement line should be:
line = line.replace('\xa0',' ')
to circumvent the problem.
If you know what the format is you can do the correct conversion yourself, but that should not be necessary and that or the above patching is not a structural solution. It would be best if the YAML file was generated in a correct way (they default to UTF-8, so it should contain correct UTF-8). It could UTF-16 without the appropriate BOM (which the yaml library interprets IIRC).
s1 = 'abc\\xa0xyz'
print(repr(s1))
u1 = s1.decode('utf-8') # this works fine
s = 'abc\xa0xyz'
print(repr(s))
u = s.decode('utf-8') # this throws an error

Python HTMLParser Not Reading Whole File

from HTMLParser import HTMLParser
class HTMLParserDos(HTMLParser):
full_text = ""
def handle_data(self, data):
self.full_text += data
return self.full_text
h = HTMLParserDos()
file = open('emails.txt', 'r')
h.feed(file.read())
file.close()
print h.container
This code is getting an error:
Traceback (most recent call last): File "/Users/laurenstrom/Google
Drive/PYTHON/RANDO_CALRISSIAN/html_parse", line 15, in
h.feed(file.read()) File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/HTMLParser.py",
line 108, in feed
self.goahead(0) File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/HTMLParser.py",
line 148, in goahead
k = self.parse_starttag(i) File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/HTMLParser.py",
line 229, in parse_starttag
endpos = self.check_for_whole_start_tag(i) File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/HTMLParser.py",
line 304, in check_for_whole_start_tag
self.error("malformed start tag") File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/HTMLParser.py",
line 115, in error
raise HTMLParseError(message, self.getpos()) HTMLParseError: malformed start tag, at line 7, column 18
I'm not sure what I'm missing about .feed() but I can't seem to find anything about why it won't just read the whole file.
Your are asking the HTML parser to parse a file most of which isn't HTML. It is tripping over line 7 of your file. Which is :
Return-Path: <Tom#sjnetworkconsulting.com>
I would imagine it is seeing the < and assuming that is HTML which of course it is not.

Scrapy response.replace encoding error

I am trying to replace the response body of a search result block of a search result page of google using response.replace() and I face some encoding issues.
scrapy shell "http://www.google.de/search?q=Zuckerccc"
>>> srb = hxs.select("//li[#class='g']").extract()
>>> body = '<html><body>' + srb[0] + '</body></html>' # get only 1st search result block
>>> b = response.replace(body = body)
Traceback (most recent call last):
File "<console>", line 1, in <module>
File "scrapy/lib/python2.6/site-packages/scrapy/http/response/text.py", line 54, in replace
return Response.replace(self, *args, **kwargs)
File "scrapy/lib/python2.6/site-packages/scrapy/http/response/__init__.py", line 77, in replace
return cls(*args, **kwargs)
File "scrapy/lib/python2.6/site-packages/scrapy/http/response/text.py", line 31, in __init__
super(TextResponse, self).__init__(*args, **kwargs)
File "scrapy/lib/python2.6/site-packages/scrapy/http/response/__init__.py", line 19, in __init__
self._set_body(body)
File "scrapy/lib/python2.6/site-packages/scrapy/http/response/text.py", line 48, in _set_body
self._body = body.encode(self._encoding)
File "../local_1/Linux-2.6c2.5-x86_64/Python/Python-147.0-0/lib/python2.6/encodings/cp1252.py", line 12, in encode
return codecs.charmap_encode(input,errors,encoding_table)
UnicodeEncodeError: 'charmap' codec can't encode character u'\u0131' in position 529: character maps to <undefined>
I tried to create my own response as well,
>>> x = HtmlResponse("http://www.google.de/search?q=Zuckerccc", body = body, encoding = response.encoding)
Traceback (most recent call last):
File "<console>", line 1, in <module>
File "scrapy/lib/python2.6/site-packages/scrapy/http/response/text.py", line 31, in __init__
super(TextResponse, self).__init__(*args, **kwargs)
self._set_body(body)
File "scrapy/lib/python2.6/site-packages/scrapy/http/response/text.py", line 48, in _set_body
self._body = body.encode(self._encoding)
File "../local_1/Linux-2.6c2.5-x86_64/Python/Python-147.0-0/lib/python2.6/encodings/cp1252.py", line 12, in encode
return codecs.charmap_encode(input,errors,encoding_table)
UnicodeEncodeError: 'charmap' codec can't encode character u'\u0131' in position 529: character maps to <undefined>
File "scrapy/lib/python2.6/site-packages/scrapy/http/response/__init__.py", line 19, in __init__
Also, when I use _body_declared_encoding() for encoding in replace() function, it works.
replace(body = body, encoding = response._body_declared_encoding())
I don't understand why response._body_declared_encoding() and response.encoding are different. Can anybody please shed some light on this.
So, what will be a good way to fix this ?
I successfully replaced the response body with these lines of code:
scrapy shell "http://www.google.de/search?q=Zuckerccc"
>>> google_result = response.xpath('//li[#class="g"]').extract()[0]
>>> body = '<html><body>' + google_result + '</body></html>'
>>> b = response.replace(body = body)
I check the source code from scrapy.http.response.text , when we use TextResponse, we need to tell self._encoding first. So we can do like this:
>>>response._encoding='utf8'
>>>response._set_body("aaaaaa")
>>>response.body
>>>'aaaaaa'

Trouble using gdata and Unicode Cyrillic in Python

I have this code
# -*- coding: utf8 -*-
__author__ = 'user'
import gdata.youtube.service
yt_service = gdata.youtube.service.YouTubeService()
query = gdata.youtube.service.YouTubeVideoQuery()
query.vq = u"не"
feed = yt_service.YouTubeQuery(query)
for yt_item in feed.entry:
print yt_item.GetSwfUrl()
And I am getting this error:
Traceback (most recent call last):
File "cyr_search.py", line 7, in
feed = yt_service.YouTubeQuery(query)
File "/Users/user/Documents/GrabaHeroku/graba_h_ve/lib/python2.7/site-packages/gdata/youtube/service.py", line 1346, in YouTubeQuery
result = self.Query(query.ToUri())
File "/Users/user/Documents/GrabaHeroku/graba_h_ve/lib/python2.7/site-packages/gdata/service.py", line 1715, in ToUri
return atom.service.BuildUri(q_feed, self)
File "/Users/user/Documents/GrabaHeroku/graba_h_ve/lib/python2.7/site-packages/atom/service.py", line 584, in BuildUri
parameter_list = DictionaryToParamList(url_params, escape_params)
File "/Users/user/Documents/GrabaHeroku/graba_h_ve/lib/python2.7/site-packages/atom/service.py", line 551, in DictionaryToParamList
for param, value in (url_parameters or {}).items()]
File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/urllib.py", line 1275, in quote_plus
return quote(s, safe)
File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/urllib.py", line 1268, in quote
return ''.join(map(quoter, s))
KeyError: u'\u043d'
How do I search for non-ASCII. Do I need to url encode the query? I thought the library will do that on its own.
Change to:
query.vq = u"не".encode('utf8')
The string needs to be encoded before being sent.

How to fix encoding in Python Mechanize?

here is the sample code:
from mechanize import Browser
br = Browser()
page = br.open('http://hunters.tclans.ru/news.php?readmore=2')
br.form = br.forms().next()
print br.form
The problem is that server return incorrect encoding (windows-cp1251). How can I manually set the encoding of the current page in mechanize?
Error:
Traceback (most recent call last):
File "/tmp/stackoverflow.py", line 5, in <module>
br.form = br.forms().next()
File "/usr/local/lib/python2.6/dist-packages/mechanize/_mechanize.py", line 426, in forms
return self._factory.forms()
File "/usr/local/lib/python2.6/dist-packages/mechanize/_html.py", line 559, in forms
self._forms_factory.forms())
File "/usr/local/lib/python2.6/dist-packages/mechanize/_html.py", line 225, in forms
_urlunparse=_rfc3986.urlunsplit,
File "/usr/local/lib/python2.6/dist-packages/ClientForm.py", line 967, in ParseResponseEx
_urlunparse=_urlunparse,
File "/usr/local/lib/python2.6/dist-packages/ClientForm.py", line 1104, in _ParseFileEx
fp.feed(data)
File "/usr/local/lib/python2.6/dist-packages/ClientForm.py", line 870, in feed
sgmllib.SGMLParser.feed(self, data)
File "/usr/lib/python2.6/sgmllib.py", line 104, in feed
self.goahead(0)
File "/usr/lib/python2.6/sgmllib.py", line 193, in goahead
self.handle_entityref(name)
File "/usr/local/lib/python2.6/dist-packages/ClientForm.py", line 751, in handle_entityref
'&%s;' % name, self._entitydefs, self._encoding))
File "/usr/local/lib/python2.6/dist-packages/ClientForm.py", line 238, in unescape
return re.sub(r"&#?[A-Za-z0-9]+?;", replace_entities, data)
File "/usr/lib/python2.6/re.py", line 151, in sub
return _compile(pattern, 0).sub(repl, string, count)
File "/usr/local/lib/python2.6/dist-packages/ClientForm.py", line 230, in replace_entities
repl = repl.encode(encoding)
LookupError: unknown encoding: windows-cp1251
I don't know about Mechanize, but you could hack codecs to accept wrong encoding names that have both ‘windows’ and ‘cp’:
>>> def fixcp(name):
... if name.lower().startswith('windows-cp'):
... try:
... return codecs.lookup(name[:8]+name[10:])
... except LookupError:
... pass
... return None
...
>>> codecs.register(fixcp)
>>> '\xcd\xe0\xef\xee\xec\xe8\xed\xe0\xe5\xec'.decode('windows-cp1251')
u'Напоминаем'
Fixed by setting
br._factory.encoding = enc
br._factory._forms_factory.encoding = enc
br._factory._links_factory._encoding = enc
(note the underscores) after br.open()

Categories

Resources