create a new patent retrieval function (Google URL)

1- the old RIS url is not functional anymore, so need to
   parse HTML...
2- require BeautifulSoup to do it
3- the authors list is properly comma-joined this time

fix #110


Former-commit-id: e05195236de8b2f1c44fc216900b5257b01c0b39

ippisite/db.sqlite3.REMOVED.git-id

-a09756589adb11dcccd5c98f7aaa3e2439d58355
\ No newline at end of file
+fedac345bcf7c524515fb3711f9b9a29e0dbf726
\ No newline at end of file

ippisite/ippidb/ws.py

@@ -2,7 +2,7 @@ from bioservices.eutils import EUtils
 from bioservices.uniprot import UniProt
 import xml.etree.ElementTree as ET
 import requests
-
+from bs4 import BeautifulSoup
 
 def get_pubmed_info(pmid):
     eu = EUtils()
@@ -26,6 +26,7 @@ def get_pubmed_info(pmid):
 
 
 def get_epo_info(patent_number):
+    """ warning: this is not to be used anymore, the 3.1 version of the EPO service is now offline """ 
     resp = requests.get(
         'http://ops.epo.org/3.1/rest-services/published-data/publication/docdb/{}/biblio.json'.format(patent_number))
     data = resp.json()
@@ -44,7 +45,8 @@ def get_epo_info(patent_number):
             'biblio_year': biblio_year,
             'authors_list': authors}
 
-def get_google_patent_info(patent_number):
+def get_google_patent_info_ris(patent_number):
+    """ warning: now offline """ 
     url = 'https://encrypted.google.com/patents/{}.ris'.format(patent_number)
     resp = requests.get(url)
     title = None
@@ -63,6 +65,21 @@ def get_google_patent_info(patent_number):
             'biblio_year': biblio_year,
             'authors_list': authors}
 
+def get_google_patent_info(patent_number):
+    url = 'https://encrypted.google.com/patents/{}'.format(patent_number)
+    resp = requests.get(url)
+    soup = BeautifulSoup(resp.text, 'html.parser')
+    title = soup.find_all('meta',attrs={'name':'DC.title'})[0]['content'].strip()
+    authors_list = []
+    for author_meta in soup.find_all('meta',attrs={'name':'DC.contributor'}):
+        authors_list.append(author_meta['content'].strip())
+    authors = ', '.join(authors_list)
+    biblio_year = soup.find_all('meta',attrs={'name':'DC.date'})[0]['content'].strip()[0:4]
+    return {'title': title,
+            'journal_name': None,
+            'biblio_year': biblio_year,
+            'authors_list': authors}
+
 def get_uniprot_info(uniprot_id):
     uniprot_client = UniProt()
     ns = {'u': 'http://uniprot.org/uniprot'}

ippisite/requirements.txt

@@ -16,3 +16,4 @@ scipy
 matplotlib==2.2.3 #Matplotlib 3.0+ does not support Python 2.x, 3.0, 3.1, 3.2, 3.3, or 3.4.
 psycopg2
 openbabel
+bs4
\ No newline at end of file

ippisite/requirements_centos.txt

@@ -15,3 +15,4 @@ sklearn
 scipy
 matplotlib==2.2.3 #Matplotlib 3.0+ does not support Python 2.x, 3.0, 3.1, 3.2, 3.3, or 3.4.
 psycopg2
+bs4
\ No newline at end of file

ippisite/requirements_rachel.txt

@@ -12,3 +12,4 @@ mod_wsgi
 bioblend
 django-allauth
 #pygraphviz>=1.3 --install-option="--include-path=/usr/local/include/graphviz/" --install-option="--library-path=/usr/local/lib/graphviz"
+bs4
\ No newline at end of file