Python獲取暗黑破壞神3戰網前1000命位玩家的英雄技能統計

# -*- coding: utf-8 -*-
"""
Diablo3 排名前1000玩家英雄使用技能統計

python diablo.py help
python diablo.py [barbarian|crusader|demon-hunter|monk'|witch-doctor|wizard]

默認使用的是亞服的數據，如果需要美服或歐服，更改`_rank_page`和`_api`變量地址即可

Copyright (c) 2015 JinnLynn 
Released under the terms of the MIT license.
"""
from __future__ import unicode_literals, print_function, absolute_import
import os
import sys
import urllib2
import json
import re

__version__ = '1.0.0'
__author__ = 'JinnLynn '
__license__ = 'The MIT License'
__copyright__ = 'Copyright 2015 JinnLynn'

# 排名頁面
_rank_page = 'http://tw.battle.net/d3/zh/rankings/'
# api
_api = 'http://tw.battle.net/api/d3/'
_api_profile = os.path.join(_api, 'profile')
_api_data = os.path.join(_api, 'data')

_hero_classes = {
 'barbarian': '野蠻人', 'crusader': '聖教軍', 'demon-hunter': '狩魔獵人',
 'monk': '武僧', 'witch-doctor': '巫醫', 'wizard': '秘術師'}

_retry = 5

_hero_class = ''
_active_skills = {}
_passive_skills = {}
_unique_gems = {}


def _clear_output(msg=''):
 sys.stdout.write('
{:30}'.format(' '))
 sys.stdout.write('
{}'.format(msg))
 sys.stdout.flush()


def _process(stated, total):
 msg = '英雄數據分析中... {}/{}'.format(stated, total)
 _clear_output(msg)


def _get(url, is_json=True):
 # print('GET: ', url)
 retry = 5 if _retry < 1 else _retry
 while retry > 0:
 try:
 req = urllib2.urlopen(url.encode('utf8'), timeout=10)
 return json.load(req) if is_json else req.read()
 except KeyboardInterrupt, e:
 raise e
 except Exception, e:
 retry -= 1
 # print('retry', retry, e)
 # raise e


def _api_url(*args, **kwargs):
 slash = kwargs.get('slash', False)
 args = [unicode(arg) for arg in args]
 url = os.path.join(*args).rstrip('/')
 return url + '/' if slash else url


def get_era():
 req = urllib2.urlopen(_rank_page)
 return req.geturl().split('/')[-2]


def get_rank_page_url(era):
 url_part = 'rift-'
 if _hero_class == 'demon-hunter':
 url_part += 'dh'
 elif _hero_class == 'witch-doctor':
 url_part += 'wd'
 else:
 url_part += _hero_class
 return os.path.join(_rank_page, 'era', era, url_part)


def fetch_rank_list():
 tags = []
 try:
 _clear_output('獲取當前游戲紀元...')
 era = get_era()
 _clear_output('獲取當前排名前1000的玩家...')
 url = get_rank_page_url(era)
 html = _get(url, is_json=False)
 # re parse
 lst = re.findall(
 r"a href="(.*)" title=.*class="icon-profile link-first">",
 html.decode('utf8'),
 re.UNICODE)
 # BeautifulSoup parse
 # import bs4
 # soup = bs4.BeautifulSoup(html)
 # lst = soup.select('#ladders-table tbody tr .battletag a')['href']
 for item in lst:
 try:
 tags.append(item.split('/')[-2])
 except:
 pass
 except Exception, e:
 print('fetch rank list fail. {}'.format(_rank_page))
 raise e
 return tags


def get_hero(player_tag):
 url = _api_url(_api_profile, player_tag, slash=True)
 data = _get(url)
 hero_selected = None
 for hero in data.get('heroes', []):
 if hero['class'] != _hero_class:
 continue
 last_updated = hero_selected['last-updated']
 # 最近使用的英雄
 if hero_selected is None or last_updated < hero['last-updated']:
 hero_selected = hero
 if not hero_selected:
 raise Exception('{} hero missing.'.format(player_tag))
 url = _api_url(_api_profile, player_tag, 'hero', hero_selected['id'])
 return _get(url)


# 主動技能符文
def stat_active_skill_rune(skill_slug, rune):
 global _active_skills
 if not rune:
 return
 slug = rune.get('slug')
 if slug in _active_skills[skill_slug]['rune']:
 _active_skills[skill_slug]['rune'][slug]['count'] += 1
 else:
 _active_skills[skill_slug]['rune'][slug] = {
 'count': 1,
 'name': rune.get('name')
 }


# 主動技能
def stat_active_skill(active):
 global _active_skills
 slug = active.get('skill', {}).get('slug')
 # d3 API 返回的數據中可能存在空的數據
 if not slug:
 return
 if slug in _active_skills:
 _active_skills[slug]['count'] += 1
 else:
 _active_skills[slug] = {
 'count': 1,
 'name': active.get('skill').get('name'),
 'rune': {}
 }
 stat_active_skill_rune(slug, active.get('rune'))


# 被動技能
def stat_passive_skill(passive):
 global _passive_skills
 slug = passive.get('skill', {}).get('slug')
 # d3 API 返回的數據中可能存在空的數據
 if not slug:
 return
 if slug in _passive_skills:
 _passive_skills[slug]['count'] += 1
 else:
 _passive_skills[slug] = {
 'count': 1,
 'name': passive.get('skill').get('name')
 }


def stat_unique_gem(items):
 global _unique_gems

 def get_gem(tooltip):
 if not tooltip:
 return None, None
 url = _api_url(_api_data, tooltip)
 data = _get(url)
 gems = data.get('gems')
 if not gems:
 return None, None
 gem = gems[0].get('item', {})
 return gem.get('id'), gem.get('name')

 if not items:
 return

 lst = [items.get(s, {}) for s in ['leftFinger', 'rightFinger', 'neck']]
 for tooltip in [d.get('tooltipParams', None) for d in lst]:
 id_, name = get_gem(tooltip)
 if not id_:
 continue
 if id_ in _unique_gems:
 _unique_gems[id_]['count'] += 1
 else:
 _unique_gems[id_] = {
 'count': 1,
 'name': name
 }


def stat(hero):
 global _active_skills, _passive_skills

 map(stat_active_skill, hero.get('skills', {}).get('active', []))
 map(stat_passive_skill, hero.get('skills', {}).get('passive', []))

 items = hero.get('items', {})
 stat_unique_gem(items)


def output(hero_stated, hero_stat_failed):
 def sort(data, count=10):
 d = sorted(data.items(), key=lambda d: d[1]['count'], reverse=True)
 return d if count <= 0 else d[0:count]

 _clear_output()

 # print('======')
 # print(hero_stated, hero_stat_failed)
 # print('======')
 # pprint(_active_skills)
 # print('======')
 # pprint(_passive_skills)
 # print('======')
 # pprint(_unique_gems)
 # pprint(_active_skills.items())
 # print('======')

 print('
=== RESULT ===
')
 print('統計英雄數
')
 print(' 成功: {} 失敗: {}
'.format(hero_stated, hero_stat_failed))

 print('主動技能使用排名: ')
 for _, d in sort(_active_skills):
 runes = []
 for _, r in sort(d.get('rune', {})):
 runes.append('{name}[{count}]'.format(**r))
 d.update({'rune_rank': ', '.join(runes)})
 print(' {name}[{count}]: {rune_rank}'.format(**d))
 print()

 print('被動技能使用排名: ')
 for _, d in sort(_passive_skills):
 print(' {name}[{count}]'.format(**d))
 print()

 print('傳奇寶石使用排名: ')
 for _, d in sort(_unique_gems):
 print(' {name}[{count}]'.format(**d))
 print()


def prepare():
 global _hero_class

 def print_hc():
 print('僅支持以下英雄類型, 默認 demon-hunter:
')
 for c, n in _hero_classes.items():
 print(c, ':', n)

 if len(sys.argv) == 1:
 _hero_class = 'demon-hunter'
 elif len(sys.argv) > 2:
 sys.exit('參數錯誤')
 else:
 arg = sys.argv[1]
 if arg == 'help':
 print_hc()
 print('
Tips: 運行中可隨時Ctrl+C終止以獲得已統計的數據結果')
 sys.exit()
 elif arg not in _hero_classes:
 print_hc()
 sys.exit()
 else:
 _hero_class = arg


def main():
 prepare()
 print('待分析的英雄類型:', _hero_classes[_hero_class])

 hero_stated = 0
 hero_stat_failed = 0
 try:
 tags = fetch_rank_list()
 if not tags:
 raise Exception('parse battle.net rank page fail.')
 except Exception, e:
 print('error,', e)
 sys.exit()

 total = len(tags)

 for tag in tags:
 try:
 hero = get_hero(tag)
 if not hero:
 raise Exception('no hero data')
 stat(hero)
 hero_stated += 1
 _process(hero_stated, total)
 except KeyboardInterrupt:
 break
 except Exception, e:
 # print('Fail: ', tag, e, hero)
 hero_stat_failed += 1

 output(hero_stated, hero_stat_failed)


if __name__ == '__main__':
 main()