3 files changed, 119 insertions, 0 deletions
diff --git a/wikifolio/__init__.py b/wikifolio/__init__.py
new file mode 100644
index 0000000..06559e1
--- /dev/null
+++ b/wikifolio/__init__.py
@@ -0,0 +1,64 @@
+import logging
+import codecs
+import time
+import urllib.request
+
+from lxml.html import parse
+
+from . import model
+
+logger = logging.getLogger(__name__)
+
+COMMENT_URL = "https://www.wikifolio.com/dynamic/de/de/invest/" \
+              "getpagedmessagesforwikifolio/{name}?Id={id}" \
+              "&tv=False" \
+              "&id={id}" \
+              "&page=1" \
+              "&pageSize=5" \
+              "&_={timestamp}"
+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)
+    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: Certificate
+    """
+    request = make_request(model.BASE_URL + name)
+    with urllib.request.urlopen(request) as input_raw:
+        document = parse(codecs.getreader('utf-8')(input_raw))
+        try:
+            return model.Certificate(
+                    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: Certificate instance
+    """
+    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:
+        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')
+            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())
diff --git a/wikifolio/model.py b/wikifolio/model.py
new file mode 100644
index 0000000..7315782
--- /dev/null
+++ b/wikifolio/model.py
@@ -0,0 +1,25 @@
+BASE_URL = "https://www.wikifolio.com/de/de/wikifolio/"
+
+
+class Certificate:
+    def __init__(self, id, shortdesc, isin, trader):
+        self.id = id
+        self.name = shortdesc
+        self.isin = isin
+        self.trader = trader
+
+    def make_url(self):
+        return BASE_URL + self.name
+
+    def __repr__(self):
+        return "<{} id={} shortdesc=\"{}\" isin={}>".format(
+                self.__class__.__name__, self.id, self.name, self.isin)
+
+
+class Comment:
+    def __init__(self, date, author, text, guid, link):
+        self.pubDate = date
+        self.author = author
+        self.description = text
+        self.guid = guid
+        self.link = link
diff --git a/wikifolio/rss.py b/wikifolio/rss.py
new file mode 100644
index 0000000..e56c143
--- /dev/null
+++ b/wikifolio/rss.py
@@ -0,0 +1,30 @@
+import time
+
+from . import model
+
+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]
+    """
+    title = "Kommentare zu {.name} / {.isin}".format(cert, cert)
+    items = []
+    for comment in comments:
+        items.append(rss20.item(
+                rss20.title(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')