async def filter_text(request):
if request.method == "GET":
text = request.args.get("text")
repl = request.args.get("repl", "*")
algorithm = request.args.get("algorithm", "bs")
else:
text = get_post_args(request, "text")
repl = get_post_args(request, "repl", "*")
algorithm = get_post_args(request, "algorithm", "bs")
if not text:
return Response.json({
"code": 400,
"message": "You should specify necessary params `text`",
"data": None
})
else:
gfw = DFAFilter() if algorithm == "dfa" else BSFilter()
gfw.parse("filter/keywords")
result = gfw.filter(message=text, repl=repl)
return Response.json({
"code": 200,
"message": "success",
"data": {
"result": result
}
})
async def match_text(request):
if request.method == "GET":
text = request.args.get("text")
algorithm = request.args.get("algorithm")
keywords = request.args.get("keywords")
else:
text = get_post_args(request, "text")
algorithm = get_post_args(request, "algorithm", "bs")
keywords = get_post_args(request, "keywords")
if not text:
return Response.json({
"code": 400,
"message": "You should specify necessary params `text`",
"data": None
})
else:
gfw = DFAFilter() if algorithm == "dfa" else BSFilter()
if keywords:
for ele in keywords:
gfw.add(ele)
else:
gfw.parse("filter/keywords")
result = list(gfw.match(message=text))
return Response.json({
"code": 200,
"message": "success",
"data": {
"result": result
}
})
def do_comment_commit(param):
content = param['body']
gfw = DFAFilter()
gfw.parse("keywords")
gfw.filter(content, "*")
param['body'] = content
res = requests.post(url + '/comment', param)
from filter import DFAFilter
f = DFAFilter()
f.add("sexy")
y = f.filter("hello sexy baby")
print(y)
from flask import Flask, render_template, jsonify, request
from filter import DFAFilter
app = Flask(__name__)
app.config["SECRET_KEY"] = "secret!" # 需要修改
gfw = DFAFilter()
gfw.parse("keywords")
@app.route("/", methods=["GET", "POST"])
def layout():
if request.method == "GET":
return """
<h1>敏感词过滤测试</h1>
<form method="POST">
<input type="text" name="wd" placeholder="test input" style="width:400px;" autofocus="autofocus"></input>
<input type="submit"></input>
</form>
"""
else:
wd = request.form.get("wd", "")
res = gfw.filter(wd)
return """
<h1>敏感词过滤测试</h1>
<form method="POST">
<input type="text" name="wd" placeholder="test input" style="width:400px;" autofocus="autofocus"></input>
<input type="submit"></input>
</form>
<h2>过滤结果：{}</h2>
<h2>是否检测到敏感词：{}</h2>
""".format(res[0], res[1])
def do_articles_all():
dict_article = [
'id', 'title', 'description', 'body', 'createat', 'updateat', 'stat',
'author', 'taglist', 'editor'
]
dict_author = ['email', 'id', 'username', 'bio', 'image']
dict_supervisor = ['id', 'status', 'remark']
dict_editor = ['id', 'decision', 'trust', 'remark']
# get all resource
articles_res_raw = requests.get(url + '/Article/')
supervisor_res_raw = requests.get(url + '/Supervisor_article/')
editor_res_raw = requests.get(url + '/Review/')
author_res_raw = requests.get(url + '/User/')
tag_res_raw = requests.get(url + '/Tag_article/')
articles_info = json.loads(articles_res_raw.text)
if len(articles_info) > 0:
articles_info = articles_info['Article']
else:
articles_info = []
supervisor_info = json.loads(supervisor_res_raw.text)
if len(supervisor_info) > 0:
supervisor_info = supervisor_info['Supervisor_article']
else:
supervisor_info = []
editor_info = json.loads(editor_res_raw.text)
if len(editor_info) > 0:
editor_info = editor_info['Review']
else:
editor_info = []
author_info = json.loads(author_res_raw.text)
if len(author_info) > 0:
author_info = author_info['User']
else:
author_info = []
tag_info = json.loads(tag_res_raw.text)
if len(tag_info) > 0:
tag_info = tag_info['Tag_article']
else:
tag_info = []
# pack article list
for each in articles_info:
# full fill article items
for item_of_article_dict in dict_article:
if item_of_article_dict not in each:
each[item_of_article_dict] = None
each.update(
{'editor': {
'supervisor': None,
'editor1': None,
'editor2': None
}})
# taglist
taglist = []
for item in tag_info:
if item['articleid'] == str(each['id']):
taglist.append(item['tag'])
if len(taglist) > 0:
each.update({'taglist': taglist})
if len(taglist) > 0:
each['taglist'] = taglist
# time
time_tmp = float(each['createat'])
each['createat'] = time.asctime(time.localtime(time_tmp))
time_tmp = float(each['updateat'])
each['updateat'] = time.asctime(time.localtime(time_tmp))
# editor
it = 1
for item in editor_info:
if item['articleid'] == each['id']:
for itor in dict_editor:
if itor not in item:
item.update({itor: None})
each['editor'].update({('editor' + str(it)): item})
it += 1
# supervisor
for item in supervisor_info:
if item['articleid'] == each['id']:
for itor in dict_supervisor:
if itor not in item:
item.update({itor: None})
each['editor'].update({'supervisor': item})
# author
for item in author_info:
if item['id'] == each['authorid']:
for itor in dict_author:
if itor not in item:
item.update({itor: None})
if 'password' in item:
item.pop('password')
each.update({'author': item})
each.pop('authorid')
# filter
content = each['body']
gfw = DFAFilter()
gfw.parse("keywords")
each['body'] = gfw.filter(content, "*")
rt = json.dumps({'articles': articles_info})
rt = json.loads(rt)
rt.update({'articlescount': len(articles_info)})
return json.dumps(rt)
def do_articles_get(param):
if 'tag' in param:
return do_article_get_by_tag(param)
dict_article = [
'id', 'title', 'description', 'body', 'createat', 'updateat', 'stat',
'author', 'taglist', 'editor'
]
dict_author = ['email', 'id', 'username', 'bio', 'image']
dict_supervisor = ['id', 'decision', 'remark']
dict_editor = ['id', 'decision', 'trust', 'remark']
# get all list
tag_article_list_raw = requests.get(url + '/Tag_article/')
tag_article_list = json.loads(tag_article_list_raw.text)
if len(tag_article_list) > 0:
tag_article_list = tag_article_list['Tag_article']
else:
tag_article_list = []
state = url + '/Article/'
param_num = 0
param = json.dumps(param)
param = json.loads(param)
if 'articleid' in param:
id_tmp = param.pop('articleid')
param.update({'id': id_tmp})
for each in param:
if param_num == 0:
state += ('?Article.' + each + '=' + str(param[each]))
param_num += 1
else:
state += ('&Article.' + each + '=' + str(param[each]))
article_list_raw = requests.get(state)
article_list = json.loads(article_list_raw.text)
if len(article_list) > 0:
article_list = article_list['Article']
else:
article_list = []
author_list_raw = requests.get(url + '/User/')
author_list = json.loads(author_list_raw.text)
if len(author_list) > 0:
author_list = author_list['User']
else:
author_list = []
supervisor_list_raw = requests.get(url + '/Supervisor_article/')
supervisor_list = json.loads(supervisor_list_raw.text)
if len(supervisor_list) > 0:
supervisor_list = supervisor_list['Supervisor_article']
else:
supervisor_list = []
editor_list_raw = requests.get(url + '/Review/')
editor_list = json.loads(editor_list_raw.text)
if len(editor_list) > 0:
editor_list = editor_list['Review']
else:
editor_list = []
tag_list_raw = requests.get(url + '/Tag_article/')
tag_list = json.loads(tag_list_raw.text)
if len(tag_list) > 0:
tag_list = tag_list['Tag_article']
else:
tag_list = []
# find by tag
articleid_list = []
for each in article_list:
articleid_list.append(each['id'])
rt_article_list = []
for each in article_list:
if each['id'] in articleid_list:
# full fill article items
for item_of_article_dict in dict_article:
if item_of_article_dict not in each:
each[item_of_article_dict] = None
each.update({
'editor': {
'supervisor': None,
'editor1': None,
'editor2': None
}
})
# taglist
taglist = []
for item in tag_list:
if item['articleid'] == str(each['id']):
taglist.append(item['tag'])
if len(taglist) > 0:
each.update({'taglist': taglist})
if len(taglist) > 0:
each['taglist'] = taglist
# time
time_tmp = float(each['createat'])
each['createat'] = time.asctime(time.localtime(time_tmp))
time_tmp = float(each['updateat'])
each['updateat'] = time.asctime(time.localtime(time_tmp))
# editor
it = 1
for item in editor_list:
if item['articleid'] == each['id']:
for itor in dict_editor:
if itor not in item:
item.update({itor: None})
item.pop('articleid')
each['editor'].update({('editor' + str(it)): item})
it += 1
# supervisor
for item in supervisor_list:
if item['articleid'] == each['id']:
for itor in dict_supervisor:
if itor not in item:
item.update({itor: None})
item.pop('articleid')
each['editor'].update({'supervisor': item})
# author
for item in author_list:
if item['id'] == each['authorid']:
for itor in dict_author:
if itor not in item:
item.update({itor: None})
if 'password' in item:
item.pop('password')
each.update({'author': item})
each.pop('authorid')
content = each['body']
gfw = DFAFilter()
gfw.parse("keywords")
each['body'] = gfw.filter(content, "*")
rt_article_list.append(each)
rt = json.dumps({'articles': rt_article_list})
rt = json.loads(rt)
rt.update({'articlescount': len(rt_article_list)})
return json.dumps(rt)
from filter import DFAFilter
gfw = DFAFilter()
gfw.parse("keywords")
print "待过滤：售假人民币 我操操操"
print "过滤后：", gfw.filter("售假人民币 我操操操", "*")