rrid annotation

rrid.py

import json, requests, re, traceback, pyramid, urlparse
from lxml import etree
try:
    from urllib.parse import urlencode
except ImportError:
    from urllib import urlencode

host = 'h.jonudell.info'  # or your own
port = 8081
host_port = 'http://' + host + ':' + str(port)

class HypothesisUtils:
    def __init__(self, username='username', password=None, limit=None, max_results=None, domain=None):
        if domain is None:
            self.domain = 'hypothes.is'
        else:
            self.domain = domain
        self.app_url = 'https://%s/app' % self.domain
        self.api_url = 'https://%s/api' % self.domain
        self.query_url = 'https://%s/api/search?{query}' % self.domain
        self.anno_url = 'https://%s/a' % domain
        self.via_url = 'https://via.hypothes.is'
        self.username = username
        self.password = password
        self.single_page_limit = 200 if limit is None else limit  # per-page, the api honors limit= up to (currently) 200
        self.multi_page_limit = 200 if max_results is None else max_results  # limit for paginated results
        self.permissions = {
                "read": ["group:__world__"],
                "update": ['acct:' + self.username + '@hypothes.is'],
                "delete": ['acct:' + self.username + '@hypothes.is'],
                "admin":  ['acct:' + self.username + '@hypothes.is']
                }

    def login(self):
        """Request an assertion, exchange it for an auth token."""
        # https://github.com/rdhyee/hypothesisapi
        r = requests.get(self.app_url)
        cookies = r.cookies
        payload = {"username":self.username,"password":self.password}
        self.csrf_token = cookies['XSRF-TOKEN']
        data = json.dumps(payload)
        headers = {'content-type':'application/json;charset=UTF-8', 'x-csrf-token': self.csrf_token}
        r = requests.post(url=self.app_url + "?__formid__=login", data=data, cookies=cookies, headers=headers)
        url = self.api_url + "/token?" + urlencode({'assertion':self.csrf_token})
        r = (requests.get(url=url,
                         cookies=cookies, headers=headers))
        self.token = r.content

    def make_annotation_payload_with_target_using_only_text_quote(self, url, prefix, exact, suffix, text, tags):
        """Create JSON payload for API call."""
        payload = {
            "uri": url,
            "user": 'acct:' + self.username + '@hypothes.is',
            "permissions": self.permissions,
            #"document": {
            #    "link": [ { "href": url } ]
            #    },
            "target": 
            [{
                "scope": [url],
                "selector": 
                    [{
                        "type": "TextQuoteSelector", 
                        "prefix": prefix,
                        "exact": exact,
                        "suffix": suffix
                        },]
                }], 
            "tags": tags,
            "text": text
        }
        return payload

    def create_annotation_with_target_using_only_text_quote(self, url=None, prefix=None, 
               exact=None, suffix=None, text=None, tags=None):
        """Call API with token and payload, create annotation (using only text quote)"""
        payload = self.make_annotation_payload_with_target_using_only_text_quote(url, prefix, exact, suffix, text, tags)
        r = self.post_annotation(payload)
        return r

    def post_annotation(self, payload):
        headers = {'Authorization': 'Bearer ' + self.token, 'Content-Type': 'application/json;charset=utf-8' }
        data = json.dumps(payload, ensure_ascii=False)
        r = requests.post(self.api_url + '/annotations', headers=headers, data=data)
        return r

def rrid(request):   
    # http://www.jneurosci.org/content/34/24/8151.full 
    target_uri = urlparse.parse_qs(request.query_string)['uri'][0]
    r = requests.get(target_uri)
    html = r.text
    #readability_doc = readability.Document(html)
    #content_html = readability_doc.summary()
    try:
        rrid_context = re.search('(.{10}?)(RRID:\s*)([\w\-]+)(.{10}?)', html).groups()
        prefix = rrid_context[0]
        exact = rrid_context[2]
        suffix = rrid_context[3]
        resolver_uri = 'https://scicrunch.org/resolver/%s.xml' % exact
        r = requests.get(resolver_uri)
        xml = r.content
        root = etree.fromstring(xml)
        data_elements = root.findall('data')[0]
        s = ''
        for data_element in data_elements:
            name = data_element.find('name').text
            value =data_element.find('value').text
            s += '<p>%s: %s</p>' % (name, value)
        h = HypothesisUtils(username='*****', password='*****')
        h.login()
        r = h.create_annotation_with_target_using_only_text_quote(url=target_uri, prefix=prefix, exact=exact, suffix=suffix, text=s)
        print r.text
    except:
        print traceback.print_exc()
    return Response(status_int=302, location=target_uri)

if __name__ == '__main__':

    from wsgiref.simple_server import make_server
    from pyramid.config import Configurator
    from pyramid.response import Response

    config = Configurator()

    config.add_route('rrid', '/rrid')
    config.add_view(rrid, route_name='rrid')

    app = config.make_wsgi_app()
    server = make_server(host, port, app)
    server.serve_forever()