def analyze_weapon_page(pq_obj, weapon_type_name):
# 先抓出所有table.ti，数据都在这3个表格里
table_t1_group = pq_obj('table.t1')
if weapon_type_name == '狩猎笛':
if len(table_t1_group) != 4:
log('table.ti长度不为4，请检查')
return False
temp_weapon_data = OrderedDict()
# 第一个 table.t1 是该派生各级别数据（攻击，槽，斩味）
analyze_weapon_page_base_info(table_t1_group.eq(0), temp_weapon_data,
weapon_type_name)
# 第二个 table.t1 是强化素材表查询
analyze_weapon_page_upgrade_info(table_t1_group.eq(2),
temp_weapon_data)
# 第三个 table.t1 是入手方法查询
analyze_weapon_page_craft_info(table_t1_group.eq(3), temp_weapon_data)
else:
if len(table_t1_group) != 3:
log('table.ti长度不为3，请检查')
return False
temp_weapon_data = OrderedDict()
# 第一个 table.t1 是该派生各级别数据（攻击，槽，斩味）
analyze_weapon_page_base_info(table_t1_group.eq(0), temp_weapon_data,
weapon_type_name)
# 第二个 table.t1 是强化素材表查询
analyze_weapon_page_upgrade_info(table_t1_group.eq(1),
temp_weapon_data)
# 第三个 table.t1 是入手方法查询
analyze_weapon_page_craft_info(table_t1_group.eq(2), temp_weapon_data)
return temp_weapon_data
def generate_weapon_excel(weapon_all_data):
k_max = 6
m_num_max = 6
# 生成excel数据
for weapon_type, weapon_type_data in weapon_all_data.items():
headers = OrderedDict()
contents = OrderedDict()
# headers[weapon_type] = ['_index']
headers[weapon_type] = [
'name_jp', 'name_chs', 'derive', 'derive_index', 'pos'
]
contents[weapon_type] = OrderedDict()
total_index = 0
for weapon_name, weapon_data in weapon_type_data.items():
# 整理数据
total_index += 1
# weapon_data['_index'] = total_index
# # 拆分斩味数据
# for i in range(k_max):
# weapon_data['斩味+%d' % i] = weapon_data['斩味'][i] if i < len(weapon_data['斩味']) else []
# del weapon_data['斩味']
#
# # 拆分素材数据
# for m_type in ['强化', '生产']:
# if '%s素材' % m_type in weapon_data:
# for i in range(m_num_max):
# weapon_data['%s素材%d' % (m_type, i + 1)] = weapon_data['%s素材' % m_type][i]['素材名'] if i < len(
# weapon_data['%s素材' % m_type]) else ''
# weapon_data['%s素材数量%d' % (m_type, i + 1)] = weapon_data['%s素材' % m_type][i]['数量'] if i < len(
# weapon_data['%s素材' % m_type]) else ''
# del weapon_data['%s素材' % m_type]
# 调整数据
# 重新生成数据表
temp_weapon_data = OrderedDict()
for data_key, data_value in weapon_data.items():
use_header = data_key
if type(data_value) == list:
use_header = '%s[]' % data_key
data_value = ';'.join([str(value) for value in data_value])
elif type(data_value) not in [int, float, bool, str]:
data_value = str(data_value)
temp_weapon_data[use_header] = data_value
if use_header not in headers[weapon_type]:
headers[weapon_type].append(use_header)
contents[weapon_type][weapon_name] = temp_weapon_data
save_filepath = os.path.join('武器_%s.xlsx' % weapon_type)
save_to_excel(headers, contents, save_filepath)
log('武器 %s 数据保存完毕' % weapon_type)
def run_job():
if not os.path.exists(WEAPON_OBJ_FILEPATH):
weapon_all_data = get_weapon_data()
else:
weapon_all_data = load_obj(WEAPON_OBJ_FILEPATH)
wiki = HuijiWiki('mhw')
if not wiki.login('Yuee bot', '123654abC'):
log('登录失败，请检查。')
return False
if not wiki.get_edit_token():
log('获取令牌失败，请检查。')
return False
# update_weapon_data(wiki, weapon_all_data)
generate_weapon_excel(weapon_all_data)
def output_weapon_name_excel(weapon_all_data):
sheet_name = '译名对照'
# 武器excel
headers = OrderedDict()
contents = OrderedDict()
headers[sheet_name] = ['_index', '类型', '日文名', '中文名']
contents[sheet_name] = OrderedDict()
# 素材excel
headers_item = OrderedDict()
contents_item = OrderedDict()
headers_item[sheet_name] = ['_index', '日文名', '中文名']
contents_item[sheet_name] = OrderedDict()
item_name_list = []
total_index = 0
total_item_index = 0
for weapon_type, weapon_type_data in weapon_all_data.items():
for weapon_name, weapon_data in weapon_type_data.items():
# 整理数据
total_index += 1
contents[sheet_name][weapon_name] = {
'_index': total_index,
'类型': weapon_type,
'日文名': weapon_name,
'中文名': '',
}
for craft_type in ['upgrade', 'craft']:
for i in range(1, 5):
craft_key = '%s_m%d' % (craft_type, i)
if craft_key in weapon_data:
item_name = weapon_data[craft_key]
if item_name not in item_name_list:
item_name_list.append(item_name)
total_item_index += 1
contents_item[sheet_name][total_item_index] = {
'_index': total_item_index,
'日文名': item_name,
'中文名': '',
}
save_filepath = os.path.join('weapon_name.xlsx')
save_to_excel(headers, contents, save_filepath)
save_filepath = os.path.join('item_name.xlsx')
save_to_excel(headers_item, contents_item, save_filepath)
log('译名表保存完毕。')
def config_loader(config_path,
error_check_list=OrderedDict(),
section_name=''):
# 获取配置文件
if not os.path.exists(config_path):
log('配置文件《%s》未找到，请检查。' % os.path.split(config_path)[1])
return False
cfg = configparser.ConfigParser()
cfg.read(config_path)
config = OrderedDict()
for cfg_section in cfg.sections():
if cfg_section not in config:
config[cfg_section] = OrderedDict()
for cf_key, cf_value in cfg[cfg_section].items():
config[cfg_section][cf_key] = cf_value
# 错误检查
for check_section_name, check_info_list in error_check_list.items():
if check_section_name not in config:
log('配置文件错误：没有找到“%s”段落，请检查。' % check_section_name)
return False
for check_info in check_info_list:
if check_info['n'] not in config[check_section_name]:
if check_info['t'] == 'check_value':
config[check_section_name][
check_info['n']] = check_info['d']
else:
log('配置文件错误：“%s”段落中没有参数“%s”，请检查。' %
(check_section_name, check_info['n']))
return False
value = config[check_section_name][check_info['n']]
if check_info['t'] == 'path_exists':
if not os.path.exists(value):
log('文件夹未找到：“%s”，请检查。' % os.path.abspath(value))
elif check_info['t'] == 'file_exists':
if not os.path.exists(value):
log('文件未找到：“%s”，请检查。' % os.path.abspath(value))
elif check_info['t'] == 'path_create':
check_folder(value)
if section_name != '' and section_name in config:
return config[section_name]
else:
return config
def get_weapon_data():
mhwg_org = Site_MHWg_org()
# 获取首页对象
mainpage = mhwg_org.mainpage()
# 从首页获取武器列表
weapon_data = OrderedDict()
pq_weapon_a_groups = mainpage('#sc_2 a')
for weapon_type_index in range(len(pq_weapon_a_groups)):
pq_weapon_type = pq_weapon_a_groups.eq(weapon_type_index)
type_page_url = pq_weapon_type.attr('href')
weapon_type_name = WEAPON_NAME_MAP[pq_weapon_type.text()]
if weapon_type_name not in ['双剑']:
continue
weapon_data[weapon_type_name] = OrderedDict()
# 从武器列表页，获取所有武器派生页面的数据
pq_weapon_type_page = mhwg_org.get_page(type_page_url)
pq_weapon_type_a_groups = pq_weapon_type_page('.t1 a')
for weapon_index in range(len(pq_weapon_type_a_groups)):
pq_weapon = pq_weapon_type_a_groups.eq(weapon_index)
weapon_page_url = pq_weapon.attr('href')
if weapon_page_url.find('#') >= 0:
continue
pq_weapon_page = mhwg_org.get_page(weapon_page_url)
if not pq_weapon_page:
log('武器页未找到 %s' % weapon_page_url)
continue
# if weapon_page_url not in ['/ida/220824.html']:
# continue
log('开始解析 %s' % weapon_page_url)
result = analyze_weapon_page(pq_weapon_page, weapon_type_name)
if not result:
continue
weapon_data[weapon_type_name].update(result)
# save_obj(weapon_data, 'weapon_data.obj')
return weapon_data
def analyze_weapon_page_upgrade_info(info_obj, temp_weapon_data):
info_obj_tr_group = info_obj('tr')
for i in range(1, len(info_obj_tr_group)):
info_obj_tr = info_obj_tr_group.eq(i)
info_obj_td_group = info_obj_tr('td')
# 名称
weapon_name = info_obj_td_group.eq(1).text()
# 攻击力
find = re.findall(r'(.*?)\n\[巻き戻し不可\]', weapon_name)
can_not_back = False
if find:
weapon_name = find[0]
can_not_back = True
if weapon_name not in temp_weapon_data:
# log('强化部分出现了基础数据部分没有的武器名称：%s' % weapon_name)
continue
temp_weapon_info = temp_weapon_data[weapon_name]
if temp_weapon_info['atk'] == 0:
log('武器没有攻击力，可能是未完成的数据，已跳过。武器名称：%s' % weapon_name)
return False
temp_weapon_info['rare'] = int(info_obj_td_group.eq(0).text())
temp_weapon_info['can_not_back'] = can_not_back
# 可强化路线
temp_weapon_info['upgrade_target'] = []
upgrade_target_item_text = info_obj_td_group.eq(3).text()
if upgrade_target_item_text != '':
temp_weapon_info[
'upgrade_target'] = upgrade_target_item_text.split('\n')
# 强化素材
# temp_weapon_info['获得类型'] = '强化'
# temp_weapon_info['价格'] = 0
# temp_weapon_info['素材'] = []
temp_weapon_info.update(
get_material_info(info_obj_td_group.eq(2).text(), 'upgrade'))
# 强化表完成
return True
def generate_data(self, is_new=False):
self._data = OrderedDict()
if is_new:
return True
if 'data' not in self._original_data:
log('[[%s]]数据有误：未找到内容数据，请检查。' % self._title)
return False
for index in range(0, len(self._original_data['data'])):
row_data = OrderedDict()
for key_index in range(0, len(self._header)):
row_data[self._header[key_index]] = self._original_data[
'data'][index][key_index]
key = index if self._key == '' else row_data[self._key]
if self._key != '' and not key:
log('[[%s]]数据有误：第 %d 行当作KEY的“%s”值是None，请检查。' %
(self._title, index + 1, self._key))
return False
self._data[key] = row_data
return True
def read_all_sheets_from_xlsx(xls_path, mode=list()):
result_data = OrderedDict()
if not os.path.exists(xls_path):
log('[ %s ] 文件不存在！' % xls_path)
return False
# 打开工作薄
try:
data_wb = xlrd.open_workbook(xls_path)
except xlrd.biffh.XLRDError as e:
log('[ %s ] 文件打开失败！错误：' + str(e) % xls_path)
return False
# 打开工作表
sheet_names = data_wb.sheet_names()
# 读取数据
try:
for sheet_name in sheet_names:
data_ws = data_wb.sheet_by_name(sheet_name)
result_data[sheet_name] = _read_sheet_data(data_ws, mode)
except Exception as e:
log('读取EXCEL文件发生错误，请检查工作薄中的格式是否符合规范。（%s）' % e)
return result_data
def generate_header(self, is_new=False):
# 获取header
self._header = []
if is_new:
return True
if 'schema' not in self._original_data:
log('[[%s]]数据有误：未找到表头字段，请检查。' % self._title)
return False
if 'fields' not in self._original_data['schema']:
log('[[%s]]数据有误：未找到表头字段，请检查。' % self._title)
return False
for field in self._original_data['schema']['fields']:
self._header.append(field['name'])
if self._key != '' and self._key not in self._header:
log('[[%s]]数据有误：表头字段中未找到当作KEY的“%s”，请检查。' %
(self._title, self._key))
return False
return True
def read_sheet_from_xlsx(xls_path, sheet_name='', sheet_index=-1, mode=list()):
if type(mode) == str:
mode = [mode]
result_data = OrderedDict()
if not os.path.exists(xls_path):
log('[ %s ] 文件不存在！' % xls_path)
return False
# 打开工作薄
try:
data_wb = xlrd.open_workbook(xls_path)
except xlrd.biffh.XLRDError as e:
log('[ %s ] 文件打开失败！错误：' + str(e) % xls_path)
return False
# 打开工作表
try:
if sheet_index > -1:
data_ws = data_wb.sheet_by_index(sheet_index)
elif sheet_name != '':
data_ws = data_wb.sheet_by_name(sheet_name)
else:
data_ws = data_wb.sheet_by_index(0)
sheet_name = data_ws.name
except xlrd.biffh.XLRDError as e:
print(e)
return False
# 读取数据
try:
result_data[sheet_name] = _read_sheet_data(data_ws, mode)
except Exception as e:
log('读取EXCEL文件发生错误，请检查工作薄中的格式是否符合规范。（%s）' % e)
return result_data
def _log(self, text):
log(text)
def get_weapon_stat(td_obj):
stat_text = td_obj.text()
result_info = OrderedDict([('other_effect', [])])
for stat_text_one_line in stat_text.split('\n'):
stat_text_one_line = stat_text_one_line.strip()
# 攻击力
find = re.findall(r'攻撃：(\d+)', stat_text_one_line)
if find:
result_info['atk'] = int(find[0])
continue
# 孔数
find = re.findall(r'スロット：(.*)', stat_text_one_line)
if find:
if find[0] == '':
continue
result_info['socket'] = []
for socket_info in find[0].split(' '):
if socket_info == '-':
result_info['socket'].append(0)
elif socket_info == '①':
result_info['socket'].append(1)
elif socket_info == '②':
result_info['socket'].append(2)
elif socket_info == '③':
result_info['socket'].append(3)
continue
# 防御
find = re.findall(r'防御(.+)', stat_text_one_line)
if find:
result_info['def'] = int(find[0].replace('+', ''))
continue
# 会心
find = re.findall(r'会心(.+)%', stat_text_one_line)
if find:
result_info['cri'] = int(find[0].replace('+', ''))
continue
# 找属性攻击力
find = re.findall(r'(:?属性解放：)?(\D+)(\d+)', stat_text_one_line)
if find:
elem_type = find[0][1]
if elem_type in ELEMENT_MAP:
if find[0][0] == '属性解放：':
result_info['elem_release'] = True
result_info['elem'] = ELEMENT_MAP[elem_type]
result_info['elem_v'] = int(find[0][2])
continue
# 铳枪
elif elem_type in GUNLANCE_MAP:
result_info['gun_type'] = '%s%s' % (GUNLANCE_MAP[elem_type],
find[0][2])
continue
# 盾斧，剑斧的瓶
find = re.findall(r'ビン：(\D+)(\d*)', stat_text_one_line)
if find:
elem_type = find[0][0]
if elem_type in ELEMENT_MAP:
result_info['bottle'] = ELEMENT_MAP[elem_type]
result_info['bottle_v'] = 0
if find[0][1] != '':
result_info['bottle_v'] = int(find[0][1])
continue
# 龙封
find = re.findall(r'龍封力\[(.+)]', stat_text_one_line)
if find:
result_info['seal_dragon'] = find[0]
continue
# 狩猎笛
if stat_text_one_line == '■■■':
result_info['sound'] = []
all_span_obj_groups = td_obj.children('span')
for sound_span_index in range(len(all_span_obj_groups)):
sound_span_obj = all_span_obj_groups.eq(sound_span_index)
if sound_span_obj.text() != '■■■':
# log('音色提取出错，请检查')
continue
sound_color_obj_groups = sound_span_obj.eq(0).find('span')
for sound_index in range(len(sound_color_obj_groups)):
sound_color_obj = sound_color_obj_groups.eq(sound_index)
find_color = re.findall(r'color:(.*?);',
sound_color_obj.attr('style'))
if find_color:
if find_color[0] not in SOUND_COLOR_MAP:
log('音色颜色未匹配到：%s' % find_color[0])
result_info['sound'].append(
SOUND_COLOR_MAP[find_color[0]])
continue
# 操虫棍
if stat_text_one_line in CLUB_EFFECT:
result_info['effect'] = CLUB_EFFECT[stat_text_one_line]
continue
# 轻弩重弩期待值，删掉
find = re.findall(r'\(期待値：(\d+)\)', stat_text_one_line)
if find:
continue
# 轻弩重弩抖动
find = re.findall(r'ブレ：(.+)', stat_text_one_line)
if find:
result_info['bure'] = BURE_MAP[find[0]]
continue
# 强化部件
find = re.findall(r'強化パーツ：(\d+)', stat_text_one_line)
if find:
result_info['upgrade_slot'] = int(find[0])
continue
# 其他
result_info['other_effect'].append(stat_text_one_line)
return result_info
