morss: use final request url

Code is not very elegant...

README.md

@@ -251,7 +251,7 @@ options = morss.Options(csv=True) # arguments
 morss.crawler.sqlite_default = '/tmp/morss-cache.db' # sqlite cache location
 
 url = morss.UrlFix(url) # make sure the url is properly formatted
-rss = morss.FeedFetch(url, options) # this only grabs the RSS feed
+url, rss = morss.FeedFetch(url, options) # this only grabs the RSS feed
 rss = morss.FeedGather(rss, url, options) # this fills the feed and cleans it up
 
 output = morss.FeedFormat(rss, options, 'unicode') # formats final feed

morss/crawler.py

@@ -55,7 +55,7 @@ PROTOCOL = ['http', 'https']
 
 
 def get(*args, **kwargs):
-    return adv_get(*args, **kwargs)[0]
+    return adv_get(*args, **kwargs)['data']
 
 
 def adv_get(url, timeout=None, *args, **kwargs):
@@ -72,7 +72,13 @@ def adv_get(url, timeout=None, *args, **kwargs):
     contenttype = con.info().get('Content-Type', '').split(';')[0]
     encoding= detect_encoding(data, con)
 
-    return data, con, contenttype, encoding
+    return {
+        'data':data,
+        'url': con.geturl(),
+        'con': con,
+        'contenttype': contenttype,
+        'encoding': encoding
+    }
 
 
 def custom_handler(follow=None, delay=None, encoding=None):
@@ -621,7 +627,7 @@ class MySQLCacheHandler(BaseCache):
 
 
 if __name__ == '__main__':
-    data, con, contenttype, encoding = adv_get(sys.argv[1] if len(sys.argv) > 1 else 'https://morss.it')
+    req = adv_get(sys.argv[1] if len(sys.argv) > 1 else 'https://morss.it')
 
     if not sys.flags.interactive:
-        print(data.decode(encoding))
+        print(req['data'].decode(req['encoding']))

morss/feeds.py

@@ -759,8 +759,8 @@ class ItemJSON(Item, ParserJSON):
 if __name__ == '__main__':
     from . import crawler
 
-    data, con, contenttype, encoding = crawler.adv_get(sys.argv[1] if len(sys.argv) > 1 else 'https://www.nytimes.com/', follow='rss')
-    feed = parse(data, url=con.geturl(), encoding=encoding)
+    req = crawler.adv_get(sys.argv[1] if len(sys.argv) > 1 else 'https://www.nytimes.com/', follow='rss')
+    feed = parse(req['data'], url=req['url'], encoding=req['encoding'])
 
     if not sys.flags.interactive:
         for item in feed.items:

morss/morss.py

@@ -248,17 +248,17 @@ def ItemFill(item, options, feedurl='/', fast=False):
         delay = -2
 
     try:
-        data, con, contenttype, encoding = crawler.adv_get(url=link, delay=delay, timeout=TIMEOUT)
+        req = crawler.adv_get(url=link, delay=delay, timeout=TIMEOUT)
 
     except (IOError, HTTPException) as e:
         log('http error')
         return False # let's just delete errors stuff when in cache mode
 
-    if contenttype not in crawler.MIMETYPE['html'] and contenttype != 'text/plain':
+    if req['contenttype'] not in crawler.MIMETYPE['html'] and req['contenttype'] != 'text/plain':
         log('non-text page')
         return True
 
-    out = readabilite.get_article(data, url=con.geturl(), encoding_in=encoding, encoding_out='unicode')
+    out = readabilite.get_article(req['data'], url=req['url'], encoding_in=req['encoding'], encoding_out='unicode')
 
     if out is not None:
         item.content = out
@@ -303,14 +303,14 @@ def FeedFetch(url, options):
         delay = 0
 
     try:
-        xml, con, contenttype, encoding = crawler.adv_get(url=url, follow='rss', delay=delay, timeout=TIMEOUT * 2)
+        req = crawler.adv_get(url=url, follow='rss', delay=delay, timeout=TIMEOUT * 2)
 
     except (IOError, HTTPException):
         raise MorssException('Error downloading feed')
 
     if options.items:
         # using custom rules
-        rss = feeds.FeedHTML(xml, encoding=encoding)
+        rss = feeds.FeedHTML(req['data'], encoding=req['encoding'])
 
         rss.rules['title'] = options.title              if options.title        else '//head/title'
         rss.rules['desc'] = options.desc                if options.desc         else '//head/meta[@name="description"]/@content'
@@ -330,16 +330,16 @@ def FeedFetch(url, options):
 
     else:
         try:
-            rss = feeds.parse(xml, url, encoding=encoding)
+            rss = feeds.parse(req['data'], url=url, encoding=req['encoding'])
             rss = rss.convert(feeds.FeedXML)
                 # contains all fields, otherwise much-needed data can be lost
 
         except TypeError:
             log('random page')
-            log(contenttype)
+            log(req['contenttype'])
             raise MorssException('Link provided is not a valid feed')
 
-    return rss
+    return req['url'], rss
 
 
 def FeedGather(rss, url, options):
@@ -438,7 +438,7 @@ def process(url, cache=None, options=None):
     if cache:
         crawler.default_cache = crawler.SQLiteCache(cache)
 
-    rss = FeedFetch(url, options)
+    url, rss = FeedFetch(url, options)
     rss = FeedGather(rss, url, options)
 
     return FeedFormat(rss, options, 'unicode')
@@ -510,7 +510,7 @@ def cgi_app(environ, start_response):
     crawler.default_cache = crawler.SQLiteCache(os.path.join(os.getcwd(), 'morss-cache.db'))
 
     # get the work done
-    rss = FeedFetch(url, options)
+    url, rss = FeedFetch(url, options)
 
     if headers['content-type'] == 'text/xml':
         headers['content-type'] = rss.mimetype[0]
@@ -594,12 +594,12 @@ def cgi_get(environ, start_response):
     url, options = cgi_parse_environ(environ)
 
     # get page
-    data, con, contenttype, encoding = crawler.adv_get(url=url, timeout=TIMEOUT)
+    req = crawler.adv_get(url=url, timeout=TIMEOUT)
 
-    if contenttype in ['text/html', 'application/xhtml+xml', 'application/xml']:
+    if req['contenttype'] in ['text/html', 'application/xhtml+xml', 'application/xml']:
         if options.get == 'page':
-            html = readabilite.parse(data, encoding=encoding)
-            html.make_links_absolute(con.geturl())
+            html = readabilite.parse(req['data'], encoding=req['encoding'])
+            html.make_links_absolute(req['url'])
 
             kill_tags = ['script', 'iframe', 'noscript']
 
@@ -610,13 +610,13 @@ def cgi_get(environ, start_response):
             output = lxml.etree.tostring(html.getroottree(), encoding='utf-8')
 
         elif options.get == 'article':
-            output = readabilite.get_article(data, url=con.geturl(), encoding_in=encoding, encoding_out='utf-8', debug=options.debug)
+            output = readabilite.get_article(req['data'], url=req['url'], encoding_in=req['encoding'], encoding_out='utf-8', debug=options.debug)
 
         else:
             raise MorssException('no :get option passed')
 
     else:
-        output = data
+        output = req['data']
 
     # return html page
     headers = {'status': '200 OK', 'content-type': 'text/html; charset=utf-8'}
@@ -673,7 +673,7 @@ def cli_app():
 
     crawler.default_cache = crawler.SQLiteCache(os.path.expanduser('~/.cache/morss-cache.db'))
 
-    rss = FeedFetch(url, options)
+    url, rss = FeedFetch(url, options)
     rss = FeedGather(rss, url, options)
     out = FeedFormat(rss, options, 'unicode')
 

morss/readabilite.py

@@ -348,8 +348,8 @@ if __name__ == '__main__':
     import sys
     from . import crawler
 
-    data, con, contenttype, encoding = crawler.adv_get(sys.argv[1] if len(sys.argv) > 1 else 'https://morss.it')
-    article = get_article(data, url=con.geturl(), encoding_in=encoding, encoding_out='unicode')
+    req = crawler.adv_get(sys.argv[1] if len(sys.argv) > 1 else 'https://morss.it')
+    article = get_article(req['data'], url=req['url'], encoding_in=req['encoding'], encoding_out='unicode')
 
     if not sys.flags.interactive:
         print(article)