grab all my zhihu.com answers

convert.py

import sys, json, datetime

if len(sys.argv) < 2:
    filename = 'myzhihuanswers.json'
else:
    filename = sys.argv[1]
with open(filename) as jsonfile:
    lines = jsonfile.readlines()
i = 0
for pageline in lines:
    page = json.loads(pageline)
    if len(page) == 2: #paging & data
        data = page['data']
        for d in data:
            i+=1
            print i
            print d.keys()
            print datetime.datetime.fromtimestamp(d['created_time']).strftime('%Y-%m-%d %H:%M:%S')
            print d['question']['title']
            print len(d['content'])

savezhihuanswers.py

import requests

ZHIHUID=''
ZHIHU_X_UDID='""'
ZHIHU_AUTH=''

ANSWER_URL='https://www.zhihu.com/api/v4/members/{}/answers'.format(ZHIHUID)
PAYLOAD={'include': 'data[*].is_normal,content,created_time;'}

HEADERS= {
    'x-udid': ZHIHU_X_UDID,
    'authorization': ZHIHU_AUTH,
    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.82 Safari/537.36'
}

SAVETOFILE='myzhihuanswers.json'
r = requests.get(ANSWER_URL, params=PAYLOAD, headers=HEADERS)
if not r.status_code == 200:
    print 'failed: {}'.format(next_url)
    exit(1)
f = open(SAVETOFILE, 'w')
c = r.json()
while not c['paging']['is_end']:
    f.write(r.text+"\n")
    next_url = c['paging']['next']
    r = requests.get(next_url, headers=HEADERS)
    if not r.status_code == 200:
        print 'failed: {}'.format(next_url)
        break
    c = r.json()
f.write(r.text+"\n")
f.close()