Created
November 14, 2017 17:29
-
-
Save judell/443c77c16590aa6311ee53c05fa43bd6 to your computer and use it in GitHub Desktop.
genius to wapo import
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# using https://github.com/judell/Hypothesis | |
def genius_test(): | |
h = Hypothesis(username="judell", | |
token='6879-... a3df5', | |
group='Pk...EgL') | |
anno_id = '11978830' | |
genius_token = 'yOalMhaO8KhZBzqRgIe1gDvF0wGqRTF4uWHMxoxMlIrNWksSv0gJTpQM-kQR4MuU' | |
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 = '551506' | |
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 | |
filtered = [r for r in all_referents if r['annotator_login'] == 'byamberphillips'] | |
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 } | |
for item in filtered: | |
id = '/%s/' % item['id'] | |
url = 'http://' + item['path'].replace(id, '') | |
title = item['annotatable']['title'] | |
range = item['range'] | |
prefix = range['before'][-30:] | |
exact = range['content'] | |
suffix = range['after'][0:30] | |
dom = item['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) | |
print r.status_code |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment