From 413051037749da90f03055bcd305c82b1ee90afd Mon Sep 17 00:00:00 2001
From: Yves Fischer <yvesf-git@xapek.org>
Date: Tue, 1 Mar 2016 23:34:05 +0100
Subject: Add script to read trades

---
 wikifolio/__init__.py | 48 +++++++++++++++++++++++++++++++++++++++---------
 wikifolio/model.py    | 27 +++++++++++++++++++++++----
 2 files changed, 62 insertions(+), 13 deletions(-)

(limited to 'wikifolio')

diff --git a/wikifolio/__init__.py b/wikifolio/__init__.py
index 06559e1..667ca98 100644
--- a/wikifolio/__init__.py
+++ b/wikifolio/__init__.py
@@ -1,7 +1,7 @@
 import logging
 import codecs
 import time
-import urllib.request
+from urllib.request import urlopen, Request
 
 from lxml.html import parse
 
@@ -16,12 +16,17 @@ COMMENT_URL = "https://www.wikifolio.com/dynamic/de/de/invest/" \
               "&page=1" \
               "&pageSize=5" \
               "&_={timestamp}"
+TRADES_URL = "https://www.wikifolio.com/dynamic/de/de/invest/" \
+             "getpagedtradesforwikifolio/{name}?id={id}" \
+             "&page=1&pageSize=100"
 USER_AGENT = "Mozilla/4.0 (compatible; MSIE 6.0; " \
              "Windows NT 5.1; FSL 7.0.6.01001)"
 
 
 def make_request(url):
-    request = urllib.request.Request(url)
+    """:rtype: Request"""
+    logging.info("Make request: {}".format(url))
+    request = Request(url)
     request.add_header("User-Agent", USER_AGENT)
     return request
 
@@ -29,13 +34,14 @@ def make_request(url):
 def get_id_from_name(name):
     """
     :param name: sanitized name of the certificate (line in url)
-    :rtype: Certificate
+    :rtype: model.Certificate
     """
     request = make_request(model.BASE_URL + name)
-    with urllib.request.urlopen(request) as input_raw:
+    with urlopen(request) as input_raw:
         document = parse(codecs.getreader('utf-8')(input_raw))
         try:
             return model.Certificate(
+                    name,
                     document.find('//input[@id="wikifolio"]').value,
                     document.find('//input[@id="wikifolio-shortdesc"]').value,
                     document.find('//input[@id="wikifolio-isin"]').value,
@@ -45,13 +51,11 @@ def get_id_from_name(name):
 
 
 def get_comments(cert):
-    """
-    :type cert: Certificate instance
-    """
+    """:type cert: model.Certificate"""
     logger.info("Fetch comments of {.name}".format(cert))
     request = make_request(COMMENT_URL.format(
-            id=cert.id, name=cert.name, timestamp=int(time.time())))
-    with urllib.request.urlopen(request) as input_raw:
+            id=cert.guid, name=cert.name, timestamp=int(time.time())))
+    with urlopen(request) as input_raw:
         document = parse(codecs.getreader('utf-8')(input_raw))
         comments = document.findall('//div[@class="user-comment"]')
         for div_comment in comments:
@@ -62,3 +66,29 @@ def get_comments(cert):
                     div_comment.find('div[@class="message-item-content"]').text,
                     div_comment.get('id'),
                     cert.make_url())
+
+def get_trades(cert):
+    """:type cert: model.Certificate"""
+    request = make_request(TRADES_URL.format(name=cert.name, id=cert.guid))
+    with urlopen(request) as input_raw:
+        document = parse(codecs.getreader('utf-8')(input_raw))
+        trade_blocks = document.findall('//table/tr')
+
+        share_name = share_isin = None
+        for trade_block in trade_blocks:
+            typ = trade_block.find('td[2]').text.strip()
+            if typ != "": # not a continuation
+                share_name = trade_block.find('td[1]/div/a/span').text.strip()
+                share_isin = trade_block.find('td[1]/div/div').text.strip()
+            else: # a continuaton, read type from first column
+                typ = trade_block.find('td[1]/span').text.strip()
+            timestamp = trade_block.find('td[3]/div[2]').text.strip()
+            timestamp = timestamp.replace('\xa0', ' ')
+            timestamp = time.strptime(timestamp, "%d.%m.%Y %H:%M")
+            yield model.Trade(share_name,
+                              share_isin,
+                              typ,
+                              trade_block.find('td[3]/div[1]').text.strip(), #status
+                              timestamp,
+                              trade_block.find('td[4]').text.strip(), #quote
+                              trade_block.find('td[5]').text.strip()) # kurs
\ No newline at end of file
diff --git a/wikifolio/model.py b/wikifolio/model.py
index 7315782..ce8feba 100644
--- a/wikifolio/model.py
+++ b/wikifolio/model.py
@@ -2,9 +2,10 @@ BASE_URL = "https://www.wikifolio.com/de/de/wikifolio/"
 
 
 class Certificate:
-    def __init__(self, id, shortdesc, isin, trader):
-        self.id = id
-        self.name = shortdesc
+    def __init__(self, name, guid, shortdesc, isin, trader):
+        self.name = name
+        self.guid = guid
+        self.shortdesc = shortdesc
         self.isin = isin
         self.trader = trader
 
@@ -13,7 +14,7 @@ class Certificate:
 
     def __repr__(self):
         return "<{} id={} shortdesc=\"{}\" isin={}>".format(
-                self.__class__.__name__, self.id, self.name, self.isin)
+                self.__class__.__name__, self.guid, self.name, self.isin)
 
 
 class Comment:
@@ -23,3 +24,21 @@ class Comment:
         self.description = text
         self.guid = guid
         self.link = link
+
+
+class Trade:
+    TYPE_KAUF = 'Quote Kauf'
+    TYPE_VERKAUF = 'Quote Verkauf'
+
+    def __init__(self, share_name, share_isin, typ, status, timestamp, quote, volume):
+        self.share_name = share_name
+        self.share_isin = share_isin
+        self.typ = typ
+        self.status = status
+        self.timestamp = timestamp
+        self.quote = quote
+        self.volume = volume
+
+    def __repr__(self):
+        return "<{} {}".format(type(self).__name__,
+                " ".join(map(lambda kv: "{}={}".format(*kv), self.__dict__.items())))
-- 
cgit v1.2.1