Added special sessions and scraper to TN

showerst · Sep 14, 2016 · b5206b6 · b5206b6
1 parent 191d7c0
commit b5206b6
Show file tree

Hide file tree

Showing 2 changed files with 25 additions and 5 deletions.
diff --git a/openstates/tn/__init__.py b/openstates/tn/__init__.py
@@ -27,10 +27,22 @@
             'start_year': 2011, 'end_year': 2012},
         {'name': '108', 'sessions': ['108'],
             'start_year': 2013, 'end_year': 2014},
-        {'name': '109', 'sessions': ['109'],
+        {'name': '109', 'sessions': ['109','109s1','109s2'],
             'start_year': 2015, 'end_year': 2016},
     ],
     session_details={
+        '109s2': {
+            'type': 'special',
+            'start_date': datetime.date(2016, 9, 12),
+            'end_date': datetime.date(2016, 9, 14),
+            'display_name': '109th Second Extraordinary Session (September 2016)',
+            '_scraped_name': '2nd Extraordinary Session (September 2016)'},  
+        '109s1': {
+            'type': 'special',
+            'start_date': datetime.date(2016, 2, 1),
+            'end_date': datetime.date(2016, 2, 29),
+            'display_name': '109th First Extraordinary Session (February 2016)',
+            '_scraped_name': '1st Extraordinary Session (February 2015)'},                                 
         '109': {
             'type': 'primary',
             'display_name': '109th Regular Session (2015-2016)',

diff --git a/openstates/tn/bills.py b/openstates/tn/bills.py
@@ -192,16 +192,24 @@ class TNBillScraper(BillScraper):
     def scrape(self, term, chambers):
 
         #The index page gives us links to the paginated bill pages
-        index_page = 'http://wapp.capitol.tn.gov/apps/indexes/'
+        if self.metadata['session_details'][term]['type'] == 'special':
+            index_page = 'http://wapp.capitol.tn.gov/apps/indexes/SPSession1.aspx'
+            xpath = '//h4[text()="%s"]/following-sibling::table[1]/tbody/tr/td/a' % self.metadata['session_details'][term]['_scraped_name']
+        else:
+            index_page = 'http://wapp.capitol.tn.gov/apps/indexes/'
+            xpath = '//td[contains(@class,"webindex")]/a'
+
         index_list_page = self.get(index_page).text
+
         index_list_page = lxml.html.fromstring(index_list_page)
         index_list_page.make_links_absolute(index_page)
-
-        for bill_listing in index_list_page.xpath('//td[contains(@class,"webindex")]/a'):
-
+                
+        for bill_listing in index_list_page.xpath(xpath):
+                        
             bill_listing = bill_listing.attrib['href'] 
 
             bill_list_page = self.get(bill_listing).text
+
             bill_list_page = lxml.html.fromstring(bill_list_page)
             bill_list_page.make_links_absolute(bill_listing)