From ad59e2cf4579ec8b141360584b715b666844b571 Mon Sep 17 00:00:00 2001
From: Jim Miller <retiefjimm@gmail.com>
Date: Sun, 27 Sep 2020 19:50:32 -0500
Subject: [PATCH] Adding eFiction series parsing attempt to base_adapter.

---
 .../adapters/adapter_archiveofourownorg.py    |  2 +-
 fanficfare/adapters/adapter_tthfanficorg.py   |  2 +-
 fanficfare/adapters/base_adapter.py           | 48 +++++++++++++++++--
 fanficfare/geturls.py                         |  1 +
 4 files changed, 47 insertions(+), 6 deletions(-)

diff --git a/fanficfare/adapters/adapter_archiveofourownorg.py b/fanficfare/adapters/adapter_archiveofourownorg.py
index be645e24..46e59c87 100644
--- a/fanficfare/adapters/adapter_archiveofourownorg.py
+++ b/fanficfare/adapters/adapter_archiveofourownorg.py
@@ -592,7 +592,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
             self.performLogin(url,data)
             # get the list page with logged in session.
 
-    def get_series_from_page(self,url,data):
+    def get_series_from_page(self,url,data,normalize=False):
         '''
         This method is to make it easier for adapters to detect a
         series URL, pick out the series metadata and list of storyUrls
diff --git a/fanficfare/adapters/adapter_tthfanficorg.py b/fanficfare/adapters/adapter_tthfanficorg.py
index 266e4589..c96a26fe 100644
--- a/fanficfare/adapters/adapter_tthfanficorg.py
+++ b/fanficfare/adapters/adapter_tthfanficorg.py
@@ -356,7 +356,7 @@ class TwistingTheHellmouthSiteAdapter(BaseSiteAdapter):
         if self.getConfig("is_adult"):
             self.setSiteMaxRating(url)
 
-    def get_series_from_page(self,url,data):
+    def get_series_from_page(self,url,data,normalize=False):
         '''
         This method is to make it easier for adapters to detect a
         series URL, pick out the series metadata and list of storyUrls
diff --git a/fanficfare/adapters/base_adapter.py b/fanficfare/adapters/base_adapter.py
index ab8bf018..140c979a 100644
--- a/fanficfare/adapters/base_adapter.py
+++ b/fanficfare/adapters/base_adapter.py
@@ -411,8 +411,8 @@ class BaseSiteAdapter(Configurable):
         self.before_get_urls_from_page(url,normalize)
 
         # this way it uses User-Agent or other special settings.
-        data = self._fetchUrl(url,usecache=False)
-        series = self.get_series_from_page(url,data)
+        data = self._fetchUrl(url,usecache=True)
+        series = self.get_series_from_page(url,data,normalize)
         if series:
             # just to make it easier for adapters.
             if isinstance(series.get('desc',None),(BeautifulSoup,Tag)):
@@ -424,16 +424,56 @@ class BaseSiteAdapter(Configurable):
                                                  configuration=self.configuration,
                                                  normalize=normalize)}
 
-    def get_series_from_page(self,url,data):
+    def get_series_from_page(self,url,data,normalize=False):
+        from ..geturls import get_urls_from_html
         '''
         This method is to make it easier for adapters to detect a
         series URL, pick out the series metadata and list of storyUrls
         to return without needing to override get_urls_from_page
         entirely.
         '''
+        # return {}
+        retval = {}
         ## return dict with at least {'urllist':['storyUrl','storyUrl',...]}
         ## 'name' and 'desc' are also used if given.
-        return {}
+
+        ## for eFiction sites:
+        ## http://www.dracoandginny.com/viewseries.php?seriesid=45
+        logger.debug("base get_series_from_page:%s"%url)
+        try:
+            if re.match(r".*viewseries\.php\?s(erie)?sid=\d+.*",url): # seriesid or ssid
+                logger.debug("Attempting eFiction get_series_from_page")
+                soup = self.make_soup(data)
+                retval = {}
+                nametag = soup.select_one('div#pagetitle')
+                if nametag:
+                    nametag.find('a').decompose()
+                    retval['name'] = stripHTML(nametag)
+                    if retval['name'].endswith(' by'):
+                        # remove trailing ' by'
+                        retval['name'] = retval['name'][:-3]
+                summaryspan = soup.select_one("div#titleblock span.label")
+                if stripHTML(summaryspan) == "Summary:":
+                    desc = ""
+                    c = summaryspan.nextSibling
+                    while not isinstance(c,Tag):
+                        desc += unicode(c)
+                        c = c.nextSibling
+                    if desc:
+                        retval['desc']=desc
+
+                # trying to get story urls for series from different
+                # eFictions is a nightmare that the pre-existing
+                # get_urls_from_html() handles well enough.  I don't
+                # think eFiction allows HTML in story desc anyway...
+                retval['urllist']=get_urls_from_html(soup,
+                                                    url,
+                                                    configuration=self.configuration,
+                                                    normalize=normalize)
+        except Exception as e:
+            logger.debug("get_series_from_page for eFiction failed:%s"%e)
+            retval = {}
+        return retval
 
     # Just for series, in case we choose to change how it's stored or represented later.
     def setSeries(self,name,num):
diff --git a/fanficfare/geturls.py b/fanficfare/geturls.py
index 006cb81f..e9d32130 100644
--- a/fanficfare/geturls.py
+++ b/fanficfare/geturls.py
@@ -81,6 +81,7 @@ def get_urls_from_html(data,url=None,configuration=None,normalize=False,email=Fa
                     urls[adapter.story.getMetadata('storyUrl')] = [href]
                 else:
                     urls[adapter.story.getMetadata('storyUrl')].append(href)
+                #logger.debug("adapter storyUrl:%s"%adapter.story.getMetadata('storyUrl'))
             except Exception as e:
                 #logger.debug e
                 pass