some refactoring before moving it to githubHEADmaster

3 files changed, 93 insertions, 66 deletions

diff --git a/wikifolio/__init__.py b/wikifolio/__init__.py
index 667ca98..6537b86 100644
--- a/wikifolio/__init__.py
+++ b/wikifolio/__init__.py
@@ -1,6 +1,8 @@
+import typing
 import logging
 import codecs
 import time
+import datetime
 from urllib.request import urlopen, Request
 
 from lxml.html import parse
@@ -14,7 +16,7 @@ COMMENT_URL = "https://www.wikifolio.com/dynamic/de/de/invest/" \
               "&tv=False" \
               "&id={id}" \
               "&page=1" \
-              "&pageSize=5" \
+              "&pageSize=15" \
               "&_={timestamp}"
 TRADES_URL = "https://www.wikifolio.com/dynamic/de/de/invest/" \
              "getpagedtradesforwikifolio/{name}?id={id}" \
@@ -23,49 +25,44 @@ USER_AGENT = "Mozilla/4.0 (compatible; MSIE 6.0; " \
              "Windows NT 5.1; FSL 7.0.6.01001)"
 
 
-def make_request(url):
-    """:rtype: Request"""
+def make_request(url) -> Request:
     logging.info("Make request: {}".format(url))
     request = Request(url)
     request.add_header("User-Agent", USER_AGENT)
     return request
 
 
-def get_id_from_name(name):
-    """
-    :param name: sanitized name of the certificate (line in url)
-    :rtype: model.Certificate
-    """
+def get_id_from_name(name: str) -> model.Certificate:
     request = make_request(model.BASE_URL + name)
     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,
-                    document.find('//div[@data-trader]').get('data-trader'))
+                name,
+                document.find('//input[@id="wikifolio"]').value,
+                document.find('//input[@id="wikifolio-shortdesc"]').value,
+                document.find('//input[@id="wikifolio-isin"]').value,
+                document.find('//div[@data-trader]').get('data-trader'))
         except:
             raise Exception("Failed to find wikifolio infos (id,name,isin) in html page")
 
 
-def get_comments(cert):
-    """:type cert: model.Certificate"""
+def get_comments(cert: model.Certificate) -> typing.Iterable[model.Comment]:
     logger.info("Fetch comments of {.name}".format(cert))
     request = make_request(COMMENT_URL.format(
-            id=cert.guid, name=cert.name, timestamp=int(time.time())))
+        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:
-            pubDate = div_comment.find('div/time').get('datetime')
+            pub_date = div_comment.find('div/time').get('datetime')
             yield model.Comment(
-                    time.strptime(pubDate, "%d.%m.%Y %H:%M:%S"),
-                    "{trader} <{trader}@localhost>".format(trader=cert.trader),
-                    div_comment.find('div[@class="message-item-content"]').text,
-                    div_comment.get('id'),
-                    cert.make_url())
+                time.strptime(pub_date, "%d.%m.%Y %H:%M:%S"),
+                "{trader} <{trader}@localhost>".format(trader=cert.trader),
+                div_comment.find('div[@class="message-item-content"]').text,
+                div_comment.get('id'),
+                cert.make_url())
+
 
 def get_trades(cert):
     """:type cert: model.Certificate"""
@@ -74,21 +71,30 @@ def get_trades(cert):
         document = parse(codecs.getreader('utf-8')(input_raw))
         trade_blocks = document.findall('//table/tr')
 
-        share_name = share_isin = None
+        share_name = share_isin = kurs = None
+        trades = []
         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
+            try:
+                typ = trade_block.find('td[2]').text.strip()
+                if typ != "" and trade_block.find('td[1]/div/a/span') is not None:  # 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()
+                if trade_block.find('td[4]').text and trade_block.find('td[4]').text.strip() != "":
+                    kurs = trade_block.find('td[4]').text.strip().replace('.', '').replace(',', '.')
+                volume = trade_block.find('td[5]').text.strip().replace('.', '').replace(',', '.')
+                timestamp = trade_block.find('td[3]/div[2]').text.strip()
+                timestamp = timestamp.replace('\xa0', ' ')
+                timestamp = datetime.datetime.strptime(timestamp, "%d.%m.%Y %H:%M")
+                status = trade_block.find('td[3]/div[1]').text.strip()
+                if status != model.Trade.STATUS_AUSGEFUEHRT:
+                    continue  # skip pending ones
+
+                trades.append(model.Trade(
+                    share_name, share_isin, typ, status, timestamp, float(kurs), float(volume)
+                ))
+            except:
+                raise Exception("failed to decode trade")  # to do: where?
+
+        return trades
diff --git a/wikifolio/model.py b/wikifolio/model.py
index ce8feba..658f8ef 100644
--- a/wikifolio/model.py
+++ b/wikifolio/model.py
@@ -1,7 +1,13 @@
 BASE_URL = "https://www.wikifolio.com/de/de/wikifolio/"
 
 
-class Certificate:
+class _WithRepr:
+    def __repr__(self):
+        return "<{} {}".format(type(self).__name__,
+                               " ".join(map(lambda kv: "{}={}".format(*kv), self.__dict__.items())))
+
+
+class Certificate(_WithRepr):
     def __init__(self, name, guid, shortdesc, isin, trader):
         self.name = name
         self.guid = guid
@@ -12,12 +18,8 @@ class Certificate:
     def make_url(self):
         return BASE_URL + self.name
 
-    def __repr__(self):
-        return "<{} id={} shortdesc=\"{}\" isin={}>".format(
-                self.__class__.__name__, self.guid, self.name, self.isin)
 
-
-class Comment:
+class Comment(_WithRepr):
     def __init__(self, date, author, text, guid, link):
         self.pubDate = date
         self.author = author
@@ -26,9 +28,12 @@ class Comment:
         self.link = link
 
 
-class Trade:
+class Trade(_WithRepr):
     TYPE_KAUF = 'Quote Kauf'
     TYPE_VERKAUF = 'Quote Verkauf'
+    TYPES_KAUF = ('Quote Kauf', 'Limit Kauf', 'Stop-Limit Kauf', 'Rückabwicklung Verkauf')
+    TYPES_VERKAUF = ('Quote Verkauf', 'Limit Verkauf', 'Stop-Limit Verkauf', 'Rückabwicklung Kauf')
+    STATUS_AUSGEFUEHRT = 'Ausgeführt'
 
     def __init__(self, share_name, share_isin, typ, status, timestamp, quote, volume):
         self.share_name = share_name
@@ -38,7 +43,3 @@ class Trade:
         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())))
diff --git a/wikifolio/rss.py b/wikifolio/rss.py
index a00191c..81e6122 100644
--- a/wikifolio/rss.py
+++ b/wikifolio/rss.py
@@ -1,30 +1,50 @@
-import time
-
 from . import model
 
+import time
+import typing
+
 from ll.xist import xsc
 from ll.xist.ns import xml, rss20
 
 
-def dump(cert, comments):
-    """
-    :type cert: model.Certificate
-    :type comments: list[model.Comment]
-    """
+def dump_comments(cert: model.Certificate, comments: typing.Iterable[model.Comment]):
     title = "{.name} / {.isin}".format(cert, cert)
     items = []
     for comment in comments:
         items.append(rss20.item(
-                rss20.title("Kommentar " + title),
-                rss20.author(comment.author),
-                rss20.pubDate(time.strftime("%a, %d %b %Y %T %z",
-                                            comment.pubDate)),
-                rss20.guid(comment.guid),
-                rss20.link(comment.link),
-                rss20.description(comment.description)
+            rss20.title("Kommentar: " + title),
+            rss20.author(comment.author),
+            rss20.pubDate(time.strftime("%a, %d %b %Y %T %z",
+                                        comment.pubDate)),
+            rss20.guid(comment.guid),
+            rss20.link(comment.link),
+            rss20.description(comment.description)
+        ))
+    return xsc.Frag(xml.XML(),
+                    rss20.rss(rss20.channel(
+                        rss20.title(title),
+                        *items
+                    ))).string('utf-8')
+
+
+def dump_trades(cert: model.Certificate, trades: typing.Iterable[model.Trade]):
+    title = "{.name} / {.isin}".format(cert, cert)
+    items = []
+    for trade in trades:
+        trade_title = trade.typ + " " + str(trade.volume) + "@" + str(trade.quote) + " " + trade.share_name
+        description = trade.typ + " " + str(trade.volume) + "@" + str(trade.quote) + " " + trade.share_name
+        description += " ( " + trade.share_isin + " ) "
+
+        items.append(rss20.item(
+            rss20.title(trade_title),
+            rss20.author(cert.name),
+            rss20.pubDate(trade.timestamp.strftime("%a, %d %b %Y %T %z")),
+            rss20.guid(trade.timestamp.strftime("%a, %d %b %Y %T %z")),
+            rss20.link(cert.make_url()),
+            rss20.description(description)
         ))
     return xsc.Frag(xml.XML(),
                     rss20.rss(rss20.channel(
-                            rss20.title(title),
-                            *items
+                        rss20.title(title),
+                        *items
                     ))).string('utf-8')