def __init__(self, logger=None):
super().__init__()
self.result_data = {}
self.msg = ''
if logger is None:
self.my_lg = set_logger(log_file_name=MY_SPIDER_LOGS_PATH +
'/阿里1688/comment/' +
str(get_shanghai_time())[0:10] + '.txt',
console_log_level=INFO,
file_log_level=ERROR)
else:
self.my_lg = logger
self.my_phantomjs = MyPhantomjs()
# 可动态执行的代码
self._exec_code = '''
self.driver.find_element_by_css_selector('div.tab-item.filter:nth-child(2)').click()
sleep(1.5)
# 向下滚动10000像素
js = 'document.body.scrollTop=10000'
self.driver.execute_script(js)
sleep(3)
'''
self.headers = {
'accept-encoding': 'gzip, deflate, br',
'accept-language': 'zh-CN,zh;q=0.9',
'user-agent': HEADERS[randint(0,
len(HEADERS) - 1)],
'accept': 'image/webp,image/apng,image/*,*/*;q=0.8',
'referer': 'https://detail.1688.com/offer/45579899125.html',
}
self.page_size = '30'
def __init__(self):
self.my_lg = set_logger(log_file_name=MY_SPIDER_LOGS_PATH +
'/all_comment/_/' +
str(get_shanghai_time())[0:10] + '.txt',
console_log_level=INFO,
file_log_level=ERROR)
self.msg = ''
def __init__(self, logger=None):
self.headers = {
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
# 'Accept-Encoding:': 'gzip',
'Accept-Language': 'zh-CN,zh;q=0.9',
'Cache-Control': 'max-age=0',
'Connection': 'keep-alive',
'Host': 's.h5.jumei.com',
'Referer': 'http://s.h5.jumei.com/yiqituan/list',
'User-Agent': HEADERS[randint(0, len(HEADERS)-1)], # 随机一个请求头
'X-Requested-With': 'XMLHttpRequest',
}
self.msg = ''
if logger is None:
self.my_lg = set_logger(
log_file_name=MY_SPIDER_LOGS_PATH + '/聚美优品/拼团/' + self.get_log_file_name_from_time() + '.txt',
console_log_level=INFO,
file_log_level=ERROR
)
else:
self.my_lg = logger
self.tab_dict = {
'母婴健康': 'coutuan_baby',
'家居': 'coutuan_furniture',
'饰品配饰': 'coutuan_jewellery',
'内衣': 'coutuan_underwear',
'食品保健': 'coutuan_food',
'美妆': 'coutuan_makeup',
'女装': 'coutuan_ladies',
'礼品箱包': 'coutuan_bag',
'数码家电': 'coutuan_3c',
'鞋类': 'coutuan_shose',
'下期预告': 'coutuan_pre',
}
def _set_logger(self, logger):
if logger is None:
self.my_lg = set_logger(log_file_name=MY_SPIDER_LOGS_PATH +
'/淘宝/淘抢购/' +
str(get_shanghai_time())[0:10] + '.txt',
console_log_level=INFO,
file_log_level=ERROR)
else:
self.my_lg = logger
def _set_logger(self, logger):
'''
设置logger
:param logger:
:return:
'''
if logger is None:
self.my_lg = set_logger(log_file_name=MY_SPIDER_LOGS_PATH +
'/淘宝/comment/' +
str(get_shanghai_time())[0:10] + '.txt',
console_log_level=INFO,
file_log_level=ERROR)
else:
self.my_lg = logger
def __init__(self, logger=None):
self.headers = {
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
# 'Accept-Encoding:': 'gzip',
'Accept-Language': 'zh-CN,zh;q=0.8',
'Cache-Control': 'max-age=0',
'Connection': 'keep-alive',
'Host': 'acs.m.taobao.com',
'User-Agent': HEADERS[randint(0, 34)] # 随机一个请求头
}
self.result_data = {}
if logger is None:
self.my_lg = set_logger(
log_file_name=MY_SPIDER_LOGS_PATH + '/淘宝/_/' + str(get_shanghai_time())[0:10] + '.txt',
console_log_level=INFO,
file_log_level=ERROR
)
else: self.my_lg = logger
self.msg = ''
def __init__(self):
self.headers = {
'Accept':
'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
# 'Accept-Encoding:': 'gzip',
'Accept-Language': 'zh-CN,zh;q=0.9',
'Cache-Control': 'max-age=0',
'Connection': 'keep-alive',
'Host': 's.h5.jumei.com',
'Referer': 'http://s.h5.jumei.com/yiqituan/list',
'User-Agent': HEADERS[randint(0,
len(HEADERS) - 1)], # 随机一个请求头
'X-Requested-With': 'XMLHttpRequest',
}
self.my_lg = set_logger(log_file_name=MY_SPIDER_LOGS_PATH +
'/聚美优品/拼团/' +
self.get_log_file_name_from_time() + '.txt',
console_log_level=INFO,
file_log_level=ERROR)
self.msg = ''
self.api_all_goods_id = {} # 预存储每个tab, index的item_list
def __init__(self, logger=None):
super().__init__()
self.result_data = {}
self.msg = ''
if logger is None:
self.my_lg = set_logger(log_file_name=MY_SPIDER_LOGS_PATH +
'/淘宝/comment/' +
str(get_shanghai_time())[0:10] + '.txt',
console_log_level=INFO,
file_log_level=ERROR)
else:
self.my_lg = logger
self.headers = {
'accept-encoding': 'gzip, deflate, br',
'accept-language': 'zh-CN,zh;q=0.9',
'user-agent': HEADERS[randint(0,
len(HEADERS) - 1)],
'accept': '*/*',
'referer': 'https://item.taobao.com/item.htm?id=555635098639',
}
self.page_size = '20' # 固定值
self.comment_page_switch_sleep_time = 1.5 # 评论下一页sleep time
def __init__(self, logger=None):
self.headers = {
'Accept':
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'Accept-Language': 'zh-CN,zh;q=0.9',
'Cache-Control': 'max-age=0',
'Connection': 'keep-alive',
'Host': 's.h5.jumei.com',
'Referer':
'https://s.h5.jumei.com/yiqituan/detail?item_id=ht180321p2453550t4&type=global_deal',
'User-Agent': HEADERS[randint(0, 34)],
'X-Requested-With': 'XMLHttpRequest',
}
self.result_data = {}
if logger is None:
self.my_lg = set_logger(
log_file_name=MY_SPIDER_LOGS_PATH + '/聚美优品/拼团/' +
self.get_log_file_name_from_time() + '.txt',
console_log_level=INFO,
file_log_level=ERROR)
else:
self.my_lg = logger
self.msg = ''
def __init__(self, logger=None):
self.headers = {
'Accept':
'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
# 'Accept-Encoding:': 'gzip',
'Accept-Language': 'zh-CN,zh;q=0.8',
'Cache-Control': 'max-age=0',
'Connection': 'keep-alive',
'Host': 'h5api.m.taobao.com',
'User-Agent': HEADERS[randint(0, 34)] # 随机一个请求头
}
if logger is None:
self.my_lg = set_logger(log_file_name=MY_SPIDER_LOGS_PATH +
'/淘宝/天天特价/' +
str(get_shanghai_time())[0:10] + '.txt',
console_log_level=INFO,
file_log_level=ERROR)
else:
self.my_lg = logger
self.msg = ''
self.main_sort = {
'495000': ['时尚女装', 'mtopjsonp2'],
'496000': ['潮流男装', 'mtopjsonp4'],
'499000': ['性感内衣', 'mtopjsonp5'],
'508000': ['家居百货', 'mtopjsonp6'],
'502000': ['品质母婴', 'mtopjsonp7'],
'503000': ['食品饮料', 'mtopjsonp8'],
'497000': ['男女鞋品', 'mtopjsonp9'], # ['497000', '498000']
'498000': ['男女鞋品', 'mtopjsonp9'],
'505000': ['美容美妆', 'mtopjsonp10'],
'500000': ['箱包配饰', 'mtopjsonp11'], # ['500000', '501000']
'501000': ['箱包配饰', 'mtopjsonp11'],
'504000': ['数码电器', 'mtopjsonp12'],
'506000': ['户外运动', 'mtopjsonp13'], # ['506000', '507000']
'507000': ['户外运动', 'mtopjsonp13'],
}
async def run_forever():
#### 实时更新数据
# ** 不能写成全局变量并放在循环中, 否则会一直记录到同一文件中, 不能实现每日一志
my_lg = set_logger(log_file_name=MY_SPIDER_LOGS_PATH + '/淘宝/天天特价/' +
str(get_shanghai_time())[0:10] + '.txt',
console_log_level=INFO,
file_log_level=ERROR)
tmp_sql_server = SqlServerMyPageInfoSaveItemPipeline()
# 由于不处理下架的商品，所以is_delete=0
sql_str = '''
select goods_id, is_delete, tejia_end_time, block_id, tag_id
from dbo.taobao_tiantiantejia
where site_id=19 and is_delete=0 and GETDATE()-modfiy_time>2 and MainGoodsID is not null
'''
try:
result = list(tmp_sql_server._select_table(sql_str=sql_str))
except TypeError:
my_lg.error('TypeError错误, 导致原因: 数据库连接失败...(可能维护中)')
return None
my_lg.info('------>>> 下面是数据库返回的所有符合条件的goods_id <<<------')
my_lg.info(str(result))
my_lg.info('--------------------------------------------------------')
my_lg.info('待更新的goods_id个数: {0}'.format(len(result)))
my_lg.info('即将开始实时更新数据, 请耐心等待...'.center(100, '#'))
index = 1
# tmp_taobao_tiantiantejia = TaoBaoTianTianTeJia(logger=my_lg)
for item in result: # 实时更新数据
if index % 50 == 0:
my_lg.info('正在重置，并与数据库建立新连接中...')
# try: del tmp_sql_server
# except: pass
# gc.collect()
tmp_sql_server = SqlServerMyPageInfoSaveItemPipeline()
my_lg.info('与数据库的新连接成功建立...')
if tmp_sql_server.is_connect_success:
tejia_end_time = item[2]
# my_lg.info(str(tejia_end_time))
if item[1] == 1: # 原先下架的商品，扫描到不处理
# tmp_sql_server.delete_taobao_tiantiantejia_expired_goods_id(goods_id=item[0])
# my_lg.info('该商品goods_id[{0}]已售完, 删除成功!'.format(item[0]))
my_lg.info(
'&&&&&& 该商品({0})原先状态为is_delete=1, 不进行实际删除操作! 索引为({1})'.
format(item[0], str(index)))
index += 1
pass
elif tejia_end_time < datetime.datetime.now():
# 过期的不删除, 降为更新为常规爆款促销商品
index = await update_expired_goods_to_normal_goods(
goods_id=item[0],
index=index,
tmp_sql_server=tmp_sql_server,
logger=my_lg)
pass
else:
# 下面为天天特价商品信息更新
'''
** 由于天天特价不会提前下架商品，就不对应更新特价时间段
'''
# # 先检查该商品在对应的子分类中是否已经被提前下架, 并获取到该商品的上下架时间
# if index % 6 == 0:
# try: del tmp_taobao_tiantiantejia
# except: pass
# gc.collect()
# tmp_taobao_tiantiantejia = TaoBaoTianTianTeJia(logger=my_lg)
#
# tmp_body = await tmp_taobao_tiantiantejia.get_one_api_body(current_page=item[4], category=item[3])
# if tmp_body == '':
# msg = '获取到的tmp_body为空str! 出错category为: ' + item[3]
# my_lg.error(msg)
# continue
#
# try:
# tmp_body = re.compile(r'\((.*?)\)').findall(tmp_body)[0]
# except IndexError:
# msg = 're筛选body时出错, 请检查! 出错category为: ' + item[3]
# my_lg.error(msg)
# continue
# tmp_sort_data = await tmp_taobao_tiantiantejia.get_sort_data_list(body=tmp_body)
# if tmp_sort_data == 'no items':
# my_lg.info('该api接口获取到的item_list为no items!请检查')
# break
# tejia_goods_list = await tmp_taobao_tiantiantejia.get_tiantiantejia_goods_list(data=tmp_sort_data)
# # my_lg.info(str(tejia_goods_list))
# await asyncio.sleep(.45)
# # my_lg.info('111')
'''
研究发现已经上架的天天特价商品不会再被官方提前下架，所以此处什么都不做，跳过
'''
# if is_in_child_sort(tejia_goods_list, goods_id=item[0]) is False: # 表示被官方提前下架
# # tmp_sql_server.delete_taobao_tiantiantejia_expired_goods_id(goods_id=item[0])
# # print('该商品goods_id[{0}]已被官方提前下架, 删除成功!'.format(item[0]))
# print('222')
# pass
# else: # 表示商品未被提前下架
my_lg.info(
'------>>>| 正在更新的goods_id为(%s) | --------->>>@ 索引值为(%s)' %
(item[0], str(index)))
taobao = TaoBaoLoginAndParse(logger=my_lg)
taobao.get_goods_data(item[0])
goods_data = taobao.deal_with_data(goods_id=item[0])
if goods_data != {}:
# tmp_time = await get_this_goods_id_tejia_time(tejia_goods_list, goods_id=item[0])
# if tmp_time != []:
# begin_time, end_time = tmp_time
#
# goods_data['goods_id'] = item[0]
# goods_data['schedule'] = [{
# 'begin_time': begin_time,
# 'end_time': end_time,
# }]
# goods_data['tejia_begin_time'], goods_data['tejia_end_time'] = await tmp_taobao_tiantiantejia.get_tejia_begin_time_and_tejia_end_time(schedule=goods_data.get('schedule', [])[0])
# await taobao.update_taobao_tiantiantejia_table(data=goods_data, pipeline=tmp_sql_server)
# else:
# my_lg.info('该goods_id不在该api接口的商品中!!')
# pass
goods_data['goods_id'] = item[0]
'''不专门更新上下架时间段'''
# goods_data['schedule'] = [{
# 'begin_time': begin_time,
# 'end_time': end_time,
# }]
# goods_data['tejia_begin_time'], goods_data['tejia_end_time'] = await tmp_taobao_tiantiantejia.get_tejia_begin_time_and_tejia_end_time(schedule=goods_data.get('schedule', [])[0])
if goods_data.get('is_delete', 0) == 1:
my_lg.info('@该商品已下架...')
await taobao.update_taobao_tiantiantejia_table(
data=goods_data, pipeline=tmp_sql_server)
else:
await asyncio.sleep(4) # 否则休息4秒
pass
await asyncio.sleep(TAOBAO_REAL_TIMES_SLEEP_TIME)
index += 1
gc.collect()
else: # 表示返回的data值为空值
my_lg.error('数据库连接失败，数据库可能关闭或者维护中')
pass
gc.collect()
my_lg.info('全部数据更新完毕'.center(100, '#')) # sleep(60*60)
if get_shanghai_time().hour == 0: # 0点以后不更新
# sleep(60 * 60 * .5)
pass
else:
sleep(5)
gc.collect()
return True
def run_forever():
#### 实时更新数据
while True:
# ** 不能写成全局变量并放在循环中, 否则会一直记录到同一文件中
my_lg = set_logger(log_file_name=MY_SPIDER_LOGS_PATH + '/淘宝/实时更新/' +
str(get_shanghai_time())[0:10] + '.txt',
console_log_level=INFO,
file_log_level=ERROR)
# tmp_sql_server = SqlServerMyPageInfoSaveItemPipeline()
tmp_sql_server = SqlPools() # 使用sqlalchemy管理数据库连接池
try:
# result = list(tmp_sql_server.select_taobao_all_goods_id())
result = tmp_sql_server.select_taobao_all_goods_id()
except TypeError:
my_lg.error('TypeError错误, 原因数据库连接失败...(可能维护中)')
result = None
if result is None:
pass
else:
my_lg.info('------>>> 下面是数据库返回的所有符合条件的goods_id <<<------')
my_lg.info(str(result))
my_lg.info(
'--------------------------------------------------------')
my_lg.info('即将开始实时更新数据, 请耐心等待...'.center(100, '#'))
index = 1
for item in result: # 实时更新数据
taobao = TaoBaoLoginAndParse(logger=my_lg)
if index % 50 == 0: # 每50次重连一次，避免单次长连无响应报错
my_lg.info('正在重置，并与数据库建立新连接中...')
# try:
# del tmp_sql_server
# except:
# pass
# gc.collect()
# tmp_sql_server = SqlServerMyPageInfoSaveItemPipeline()
tmp_sql_server = SqlPools()
my_lg.info('与数据库的新连接成功建立...')
if tmp_sql_server.is_connect_success:
my_lg.info(
'------>>>| 正在更新的goods_id为(%s) | --------->>>@ 索引值为(%s)'
% (item[0], str(index)))
data = taobao.get_goods_data(item[0])
if data.get('is_delete') == 1: # 单独处理【原先插入】就是 下架状态的商品
data['goods_id'] = item[0]
data['my_shelf_and_down_time'], data[
'delete_time'] = get_my_shelf_and_down_time_and_delete_time(
tmp_data=data,
is_delete=item[1],
MyShelfAndDownTime=item[2])
# my_lg.info('------>>>| 爬取到的数据为: ' + str(data))
taobao.to_right_and_update_data(
data, pipeline=tmp_sql_server)
sleep(TAOBAO_REAL_TIMES_SLEEP_TIME) # 避免服务器更新太频繁
index += 1
gc.collect()
continue
data = taobao.deal_with_data(goods_id=item[0])
if data != {}:
data['goods_id'] = item[0]
data['my_shelf_and_down_time'], data[
'delete_time'] = get_my_shelf_and_down_time_and_delete_time(
tmp_data=data,
is_delete=item[1],
MyShelfAndDownTime=item[2])
data['_is_price_change'], data[
'_price_change_info'] = _get_price_change_info(
old_price=item[3],
old_taobao_price=item[4],
new_price=data['price'],
new_taobao_price=data['taobao_price'])
# my_lg.info('------>>>| 爬取到的数据为: ' + str(data))
taobao.to_right_and_update_data(
data, pipeline=tmp_sql_server)
else:
my_lg.info('------>>>| 休眠5s中...')
sleep(5)
else: # 表示返回的data值为空值
my_lg.error('数据库连接失败，数据库可能关闭或者维护中')
sleep(10)
pass
index += 1
# try:
# del taobao
# except:
# pass
gc.collect()
# 国外服务器上可以缩短时间, 可以设置为0s
sleep(TAOBAO_REAL_TIMES_SLEEP_TIME) # 不能太频繁，与用户请求错开尽量
my_lg.info('全部数据更新完毕'.center(100, '#')) # sleep(60*60)
if get_shanghai_time().hour == 0: # 0点以后不更新
sleep(60 * 60 * 5.5)
else:
sleep(5)
gc.collect()
restart_program()
# coding:utf-8 ''' @author = super_fazai @File : test.py @Time : 2017/10/11 14:24 @connect : [email protected] ''' from my_logging import set_logger my_lg = set_logger(log_file_name='test.txt') my_lg.exception('啊') my_lg.info('test')
def run_forever():
while True:
# ** 不能写成全局变量并放在循环中, 否则会一直记录到同一文件中
my_lg = set_logger(log_file_name=MY_SPIDER_LOGS_PATH + '/天猫/实时更新/' +
str(get_shanghai_time())[0:10] + '.txt',
console_log_level=INFO,
file_log_level=ERROR)
#### 实时更新数据
tmp_sql_server = SqlServerMyPageInfoSaveItemPipeline()
sql_str = '''
select SiteID, GoodsID, IsDelete, MyShelfAndDownTime, Price, TaoBaoPrice
from dbo.GoodsInfoAutoGet
where (SiteID=3 or SiteID=4 or SiteID=6) and GETDATE()-ModfiyTime>0.2 and MainGoodsID is not null order by ID desc
'''
try:
result = list(tmp_sql_server._select_table(sql_str=sql_str))
except TypeError:
my_lg.error('TypeError错误, 原因数据库连接失败...(可能维护中)')
result = None
if result is None:
pass
else:
my_lg.info('------>>> 下面是数据库返回的所有符合条件的goods_id <<<------')
my_lg.info(str(result))
my_lg.info('总计待更新个数: {0}'.format(len(result)))
my_lg.info(
'--------------------------------------------------------')
my_lg.info('即将开始实时更新数据, 请耐心等待...'.center(100, '#'))
index = 1
# 释放内存,在外面声明就会占用很大的，所以此处优化内存的方法是声明后再删除释放
tmall = TmallParse(logger=my_lg)
for item in result: # 实时更新数据
if index % 5 == 0:
try:
del tmall
except:
pass
tmall = TmallParse(logger=my_lg)
gc.collect()
if index % 10 == 0: # 每10次重连一次，避免单次长连无响应报错
my_lg.info('正在重置，并与数据库建立新连接中...')
tmp_sql_server = SqlServerMyPageInfoSaveItemPipeline()
my_lg.info('与数据库的新连接成功建立...')
if tmp_sql_server.is_connect_success:
my_lg.info(
'------>>>| 正在更新的goods_id为(%s) | --------->>>@ 索引值为(%s)'
% (str(item[1]), str(index)))
tmp_item = []
if item[0] == 3: # 从数据库中取出时，先转换为对应的类型
tmp_item.append(0)
elif item[0] == 4:
tmp_item.append(1)
elif item[0] == 6:
tmp_item.append(2)
tmp_item.append(item[1])
data = tmall.get_goods_data(goods_id=tmp_item)
if isinstance(data, int): # 单独处理return 4041
index += 1
sleep(TMALL_REAL_TIMES_SLEEP_TIME)
continue
if data.get('is_delete') == 1: # 单独处理下架商品
data['goods_id'] = item[1]
data['my_shelf_and_down_time'], data[
'delete_time'] = get_my_shelf_and_down_time_and_delete_time(
tmp_data=data,
is_delete=item[2],
MyShelfAndDownTime=item[3])
# my_lg.info('------>>>| 爬取到的数据为: %s' % str(data))
tmall.to_right_and_update_data(data,
pipeline=tmp_sql_server)
sleep(TMALL_REAL_TIMES_SLEEP_TIME)
index += 1
gc.collect()
continue
data = tmall.deal_with_data()
if data != {}:
data['goods_id'] = item[1]
data['my_shelf_and_down_time'], data[
'delete_time'] = get_my_shelf_and_down_time_and_delete_time(
tmp_data=data,
is_delete=item[2],
MyShelfAndDownTime=item[3])
data['_is_price_change'], data[
'_price_change_info'] = _get_price_change_info(
old_price=item[4],
old_taobao_price=item[5],
new_price=data['price'],
new_taobao_price=data['taobao_price'])
# my_lg.info(str(data['_is_price_change']) + ' ' +str(data['_price_change_info']))
# my_lg.info('------>>>| 爬取到的数据为: %s' % str(data))
tmall.to_right_and_update_data(data,
pipeline=tmp_sql_server)
else: # 表示返回的data值为空值
my_lg.info('------>>>| 休眠8s中...')
sleep(8)
else: # 表示返回的data值为空值
my_lg.error('数据库连接失败，数据库可能关闭或者维护中')
sleep(5)
pass
index += 1
gc.collect()
sleep(TMALL_REAL_TIMES_SLEEP_TIME)
my_lg.info('全部数据更新完毕'.center(100, '#')) # sleep(60*60)
if get_shanghai_time().hour == 0: # 0点以后不更新
sleep(60 * 60 * 5.5)
else:
sleep(5)
gc.collect()
def _set_logger(self):
self.my_lg = set_logger(log_file_name=MY_SPIDER_LOGS_PATH +
'/聚美优品/拼团/' + str(get_shanghai_time())[0:10] +
'.txt',
console_log_level=INFO,
file_log_level=ERROR)
import requests
from pprint import pprint
from json import loads, dumps
import re
import asyncio
from my_logging import set_logger
from logging import INFO, ERROR
from my_utils import (
get_shanghai_time,
get_taobao_sign_and_body,
)
MY_SPIDER_LOGS_PATH = '/Users/afa/myFiles/my_spider_logs/电商项目'
my_lg = set_logger(log_file_name=MY_SPIDER_LOGS_PATH + '/淘宝/微淘/' +
str(get_shanghai_time())[0:10] + '.txt',
console_log_level=INFO,
file_log_level=ERROR)
headers = {
'accept-encoding': 'gzip, deflate, br',
'accept-language': 'zh-CN,zh;q=0.9',
'user-agent':
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36',
'accept': '*/*',
'referer':
'https://market.m.taobao.com/apps/market/content/index.html?ut_sk=1.VmYadv9DXkkDAFZm0VV4JBNq_21380790_1527298517854.Copy.33¶ms=%7B%22csid%22%3A%2254a52aea54b7c29d289a0e36b2bf2f51%22%7D&wh_weex=true&contentId=200668154273&source=weitao_2017_nocover&data_prefetch=true&suid=3D763077-A7BF-43BC-9092-C17B35E896F9&wx_navbar_transparent=false&wx_navbar_hidden=false&sourceType=other&un=bc80c9f324602d31384c4a342af87869&share_crt_v=1&sp_tk=o6R2Q0ZDMHZvaDBlS6Ok&cpp=1&shareurl=true&spm=a313p.22.68.948703884987&short_name=h.WAjz5RP&app=chrome',
'authority': 'h5api.m.taobao.com',
# cookie得注释掉, 否则为非法请求
# 'cookie': 't=70c4fb481898a67a66d437321f7b5cdf; cna=nbRZExTgqWsCAXPCa6QA5B86; l=AkFBuFEM2rj4GbU8Mjl3KsFo0YZa/7Vg; thw=cn; tracknick=%5Cu6211%5Cu662F%5Cu5DE5%5Cu53F79527%5Cu672C%5Cu4EBA; _cc_=UIHiLt3xSw%3D%3D; tg=0; enc=OFbfiyN19GGi1GicxsjVmrZoFzlt9plbuviK5OuthXYfocqTD%2BL079G%2BIt4OMg6ZrbV4veSg5SQEpzuMUgLe0w%3D%3D; hng=CN%7Czh-CN%7CCNY%7C156; miid=763730917900964122; mt=ci%3D-1_1; cookie2=16c0da3976ab60d7c87ef7cea1e83cb2; v=0; _tb_token_=dd9fe0edb4b3; tk_trace=oTRxOWSBNwn9dPy4KVJVbutfzK5InlkjwbWpxHegXyGxPdWTLVRjn23RuZzZtB1ZgD6Khe0jl%2BAoo68rryovRBE2Yp933GccTPwH%2FTbWVnqEfudSt0ozZPG%2BkA1iKeVv2L5C1tkul3c1pEAfoOzBoBsNsJyRfZ0FH5AEyz0CWtQgYlWnUAkbLeBYDpeNMwsdmBZ5GYwOAPdU1B2IUBU8G0MXGQCqFCjZt1pjb2TJN2uXIiZePpK9SWkwA%2FlD1sTTfYGTmnCo0YJ7IAG%2BnJtbITMYZ3mzYjFZtYlGojOqye861%2FNFDJbTR41FruF%2BHJRnt%2BHJNgFj3F7IDGXJCs8K; linezing_session=4ic7MPhjlPi65fN5BzW36xB7_1527299424026Fe7K_1; isg=BDo6U2SENb2uULiLxiJ4XA6ri2ZWbZPa3G9M1kQz602YN9pxLHsO1QBGg8PrpzZd; _m_h5_tk=53d85a4f43d72bc623586c142f0c5293_1527305714711; _m_h5_tk_enc=cc75764d122f72920ae715c9102701a8'
}
