Genius test

gistfile1.txt

def genius_test():

    h = Hypothesis(username="judell", 
                     token='6879- ... a3df5',
                     group='Pk ... gL')

    anno_id = '12192534'
    genius_token = 'yOalM ... R4MuU'
    url = 'https://api.genius.com/annotations/' + anno_id
    headers = {'Authorization': 'Bearer ' + genius_token, 'Content-Type': 'application/json;charset=utf-8' }
    r = requests.get(url, headers=headers)
    annotation = r.json()

    web_page_id = '560764' // 
    page = 1
    done = False
    all_referents = []
    while done is False:
        url = 'https://api.genius.com/referents?web_page_id=%s&per_page=20&page=%s' % (web_page_id, page)
        headers = {'Authorization': 'Bearer ' + genius_token, 'Content-Type': 'application/json;charset=utf-8' }
        response = requests.get(url, headers=headers)
        r = response.json()
        referents = r['response']['referents']
        if len(referents) == 0:
            done = True
        else:
            all_referents = all_referents + referents
            page = page + 1

    callums = [r for r in all_referents if r['annotator_login'] == 'CallumBorchers']

    def complex_node(node):
        tag = None
        attributes = None
        children = None
        for item in node:
            if item == 'tag': tag = node[item]
            if item == 'attributes': attributes = node[item]
            if item == 'children': children = node[item]
        return {'tag':tag, 'attributes':attributes, 'children':children }

    url = 'https://www.washingtonpost.com/news/the-fix/wp/2017/06/20/sean-spicers-off-camera-no-audio-press-briefing-annotated/'
    title = "Sean Spicer's off-camera, no-audio press briefing, annotated"

    for callum in callums:
        range = callum['range']
        prefix = range['before'][-30:]
        exact = range['content']
        suffix = range['after'][0:30]
        dom = callum['annotations'][0]['body']['dom']
        
        text = ''
        for child in dom['children']:
            if not 'children' in child:
                continue
            print child['tag']
            if child['tag'] == 'p':
                text = text + '<p>'
            nodes = child['children']
            for node in nodes:
                if type(node) is unicode:
                    text = text + node
                else:
                    complex = complex_node(node)
                    if complex['tag'] == 'a':
                        text = text + ' <a href="%s">%s</a> ' % (
                            complex['attributes']['href'],
                            complex['children'][0]
                            )
        payload = {
            "uri": url,
            "target": 
                [{
                    "source": [url],
                    "selector": 
                        [{
                            "type": "TextQuoteSelector", 
                            "prefix": prefix,
                            "exact": exact,
                            "suffix": suffix
                            }
                        ]
                }], 
            "text": text,
	        "document": {
		        "title": [title]
	        },
            "permissions": h.permissions,
            "group": h.group 
        }

        r = h.post_annotation(payload)