[Sync] Kazimir uses ALS Typograf

utils/Sync/kazimir/__init__.py

@@ -94,9 +94,11 @@ def html_from_tree(tree):
 
 
 async def typo(text):
-    url = 'http://www.typograf.ru/webservice/'
-    params = dict(text=text)
-    return await request.post(url, params, {'chr': 'utf-8'})
+    from kazimir import artlebedev
+    return await artlebedev.typograf(text)
+    # url = 'http://www.typograf.ru/webservice/'
+    # params = dict(text=text)
+    # return await request.post(url, params, {'chr': 'utf-8'})
 
 
 def join_tokens(tokens):

utils/Sync/kazimir/artlebedev.py

@@ -0,0 +1,43 @@
+from sync.data import request
+from lxml import etree
+
+
+async def typograf(text, options={}):
+    text = text.replace('&', '&')
+    text = text.replace('<', '&lt;')
+    text = text.replace('>', '&gt;')
+
+    body = '''
+    <?xml version="1.0" encoding="UTF-8"?>
+    <soap:Envelope xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:soap="http://schemas.xmlsoap.org/soap/envelope/">
+    <soap:Body>
+     <ProcessText xmlns="http://typograf.artlebedev.ru/webservices/">
+      <text>{text}</text>
+      <entityType>1</entityType>
+      <useBr>0</useBr>
+      <useP>1</useP>
+      <maxNobr>3</maxNobr>
+      </ProcessText>
+     </soap:Body>
+    </soap:Envelope>
+    '''.strip().format(text=text)
+
+    url = 'http://typograf.artlebedev.ru/webservices/typograf.asmx'
+    resp = await request.post(url, body, {}, {
+        'Content-Type': 'text/xml',
+        'SOAPAction': 'http://typograf.artlebedev.ru/webservices/ProcessText',
+    })
+
+    response_tree = etree.fromstring(resp.encode())
+
+    try:
+        # look for ProcessTextResult
+        typograf_response = response_tree.getchildren()[0].getchildren()[0].getchildren()[0].text
+    except Exception as response_tree:
+        print(response_tree)
+        return text
+
+    typograf_response = typograf_response.replace('&amp;', '&')
+    typograf_response = typograf_response.replace('&lt;', '<')
+    typograf_response = typograf_response.replace('&gt;', '>')
+    return typograf_response