Merge pull request #240 from scholarly-python-package/develop

Develop

scholarly/_navigator.py

@@ -34,6 +34,8 @@
 class DOSException(Exception):
     """DOS attack was detected."""
 
+class MaxTriesExceededException(Exception):
+    pass
 
 class Singleton(type):
     _instances = {}
@@ -65,6 +67,10 @@ def set_logger(self, enable: bool):
 
         self.logger.setLevel((logging.INFO if enable else logging.CRITICAL))
 
+    def set_timeout(self, timeout: int):
+        """Set timeout period in seconds for scholarly"""
+        if timeout >= 0:
+            self._TIMEOUT = timeout
 
     def use_proxy(self, pg: ProxyGenerator):
         if pg is not None:
@@ -149,7 +155,7 @@ def _get_page(self, pagerequest: str) -> str:
 
             tries += 1
             self._session, timeout = self.pm.get_next_proxy(num_tries = tries, old_timeout = timeout)
-        raise Exception("Cannot fetch the page from Google Scholar.")
+        raise MaxTriesExceededException("Cannot Fetch from Google Scholar.")
 
 
     def _set_retries(self, num_retries: int) -> None:
@@ -271,3 +277,28 @@ def search_author_id(self, id: str, filled: bool = False) -> Author:
         else:
             res = author_parser.fill(res, sections=['basics'])
         return res
+
+    def search_organization(self, url: str, fromauthor: bool) -> list:
+        """Generate instiution object from author search page.
+           if no results are found and `fromuthor` is True, then use the first author from the search
+           to get institution/organization name.
+        """
+        soup = self._get_soup(url)
+        rows = soup.find_all('h3', 'gsc_inst_res')
+        if rows:
+            self.logger.info("Found institution")
+
+        res = []
+        for row in rows:
+            res.append({'Organization': row.a.text, 'id': row.a['href'].split('org=', 1)[1]})
+
+        if rows == [] and fromauthor is True:
+            try:
+                auth = next(self.search_authors(url))
+                authorg = self.search_author_id(auth.id).organization
+                authorg['fromauthor'] = True
+                res.append(authorg)
+            except Exception:
+                res = []
+
+        return res

scholarly/_scholarly.py

@@ -51,11 +51,15 @@ def set_logger(self, enable: bool):
         """
         self.__nav.set_logger(enable)
 
+    def set_timeout(self, timeout: int):
+        """Set timeout period in seconds for scholarly"""
+        self.__nav.set_timeout(timeout)
+
 
     def search_pubs(self,
                     query: str, patents: bool = True,
                     citations: bool = True, year_low: int = None,
-                    year_high: int = None)->_SearchScholarIterator:
+                    year_high: int = None, sortby_date: str = None)->_SearchScholarIterator:
         """Searches by query and returns a generator of Publication objects
 
         :param query: terms to be searched
@@ -68,6 +72,8 @@ def search_pubs(self,
         :type year_low: int, optional
         :param year_high: maximum year of publication, defaults to None
         :type year_high: int, optional
+        :param sortby_date: 'abstracts' for abstracts, 'everything' for all results
+        :type sortyby_date: string, optional
         :returns: Generator of Publication objects
         :rtype: Iterator[:class:`Publication`]
 
@@ -116,8 +122,14 @@ def search_pubs(self,
         yr_hi = '&as_yhi={0}'.format(year_high) if year_high is not None else ''
         citations = '&as_vis={0}'.format(1 - int(citations))
         patents = '&as_sdt={0},33'.format(1 - int(patents))
+        sortby = ''
+
+        if sortby_date == 'abstract':
+            sortby = '&scisbd=1'
+        elif sortby_date == 'everything':
+            sortby = '&scisbd=2'
         # improve str below
-        url = url + yr_lo + yr_hi + citations + patents
+        url = url + yr_lo + yr_hi + citations + patents + sortby
         return self.__nav.search_publications(url)
 
     def search_single_pub(self, pub_title: str, filled: bool = False)->PublicationParser:
@@ -317,3 +329,20 @@ def pprint(self, object: Author or Publication)->None:
         del to_print['container_type']
         print(pprint.pformat(to_print))
 
+    def search_org(self, name: str, fromauthor: bool = False) -> list:
+        """Search by organization name and return a list of possible disambiguations
+        :Example::
+            .. testcode::
+                search_query = scholarly.search_org('ucla')
+                print(search_query)
+        :Output::
+            .. testoutput::
+                [{'Organization': 'University of California, Los Angeles',
+                  'id': '14108176128635076915'},
+                 {'Organization': 'Universidad Centroccidental Lisandro Alvarado',
+                  'id': '9670678584336165373'}
+                ]
+        """
+
+        url = _AUTHSEARCH.format(requests.utils.quote(name))
+        return self.__nav.search_organization(url, fromauthor)

setup.py

@@ -5,7 +5,7 @@
 
 setuptools.setup(
     name='scholarly',
-    version='1.0.3',
+    version='1.0.4',
     author='Steven A. Cholewiak, Panos Ipeirotis, Victor Silva',
     author_email='steven@cholewiak.com, panos@stern.nyu.edu, vsilva@ualberta.ca',
     description='Simple access to Google Scholar authors and citations',