def process_item():
try:
cookie = 'OZ_1U_2061=vid=v84a8a99a17f61.0&ctime=1481280351<ime=1481280207; otherx=e%3D1%26p%3D*%26s%3D0%26c%3D0%26f%3D0%26g%3D0%26t%3D0; mbk=5dd5b762527e7c53; _tb_token_=ee737183193e6; ck1=; uc1=cookie14=UoW%2BuvgMtNhjKA%3D%3D&lng=zh_CN&cookie16=U%2BGCWk%2F74Mx5tgzv3dWpnhjPaQ%3D%3D&existShop=false&cookie21=URm48syIYn73&tag=3&cookie15=UIHiLt3xD8xYTw%3D%3D&pas=0; uc3=sg2=Wqbxb6LyHC3oJzu6qXhfKTl7%2FAp31ETbn2A2Kj%2FuE90%3D&nk2=F5NO4MKvNg%3D%3D&id2=UNGQXF%2FfFY8%3D&vt3=F8dARVK2A0Q653XIlwM%3D&lg2=U%2BGCWk%2F75gdr5Q%3D%3D; lgc=teemimi; tracknick=teemimi; cookie2=1c98dde86727cf811a84e96da0b57801; cookie1=UNICLQDxGeiUdu2e8mzQbAdAJ72nNq7WNSx7YehUHhE%3D; unb=31634811; t=c1a07a395b20ebf0a0e52a6d601ffb71; skt=a7ef272f517551b6; _nk_=teemimi; _l_g_=Ug%3D%3D; cookie17=UNGQXF%2FfFY8%3D; hng=; uss=B0E3dfs1Nf2o7S9bOHn9v86329LgubJG5ximIyCeMFRZ%2Bv0IqJTrCxIsuZc%3D; login=true; cna=EbDKEIIrPBcCAXhVUl24UDEN; isg=AiQkkA1jIGPJ81R1qn75z7u09SIjs1NNPRl-0T5Fj--y6cazZs0Yt1of3_aL; l=AuHh2Murc/6E3948EdyV7MR4caf7sVWA'
headers.update(
Referer='https://detail.tmall.com/item.htm?id=522189908497')
headers.update(cookie=cookie)
resp = http(
'GET',
'https://bar.tmall.com/cueAssetMsg.htm?sellerId=515369883&itemId=522189908497&callback=jsonp692&_input_charset=UTF-8',
headers)
# resp,num=re.subn(r'(process_comment\()({.*})(\));',r'\1%s\2%s\3'%('\'','\''),resp)
print resp
except Exception as e:
print_err()
def process_item(page=1):
try:
resp = http(
'GET',
'http://money.finance.sina.com.cn/quotes_service/api/jsonp_v2.php/IO.XSRV2.CallbackList[\'y2PhvJWEK4sZBTJW\']/StatisticsService.getVolumeReduceConList?page=%d&num=50&sort=day_con&asc=0&node=adr_hk'
% page)
# resp,num=re.subn(r'(process_comment\()({.*})(\));',r'\1%s\2%s\3'%('\'','\''),resp)
# print resp
m = re.match(
ur'^(IO\.XSRV2\.CallbackList\[\'y2PhvJWEK4sZBTJW\'\]\()(\[\{.*\}\])(\))$',
resp)
if m:
resp = m.group(2)
process_sl(resp.decode('gbk'))
else:
print 'error in process_item '
except Exception as e:
print_err()
def followed(self, dstuid):
followedurl = "http://weibo.com/aj/f/followed?ajwvr=6&__rnd=%s" % int(
time.time())
data = {
'uid': '%s' % dstuid,
'rank': '0',
'location': 'mblog',
'_t': '0',
'extra': '',
'f': '1',
'oid': '%s' % self.uid,
'nogroup': 'false',
'challenge_uids': '',
'check_challenge_value': '',
'location': 'home',
'refer_sort': 'card',
'refer_flag': 'followed',
'refer_flag': '0000020001_',
'refer_lflag': '',
'template': '1',
}
# headers['set-cookie'] = resp.headers['set-cookie']
headers.update(Referer='http://weibo.com/u/' + self.uid +
'?topnav=1&wv=5')
result = http('POST', followedurl, headers, **data)
default_logger.info(
'-----------------result-----------------------------------')
default_logger.info(result)
default_logger.info(
'----------------------------------------------------')
result = json.loads(result)
if result['code'] == '100000':
return True
else:
default_logger.info(
'-----------------fail msg-----------------------------------')
default_logger.info(result['msg'])
default_logger.info(
'----------------------------------------------------')
return False
def get_ip(self):
print 'ddd'
sd = http('GET', 'http://1212.ip138.com/ic.asp', headers=headers)
print 'ddd,lll'
print 'dddd88ss_%s' % (sd)
def read_jingxuan_for_json(path):
data = xlrd.open_workbook(path) #打开文件
table = data.sheets()[0] #通过索引顺序获取
# table = data.sheet_by_index(0) #通过索引顺序获取
# table = data.sheet_by_name(u'Sheet1')#通过名称获取
# 获取整行和整列的值（数组）
# table.row_values(i)
# table.col_values(i)
# 获取行数和列数
nrows = table.nrows
ncols = table.ncols
print nrows, ncols
# word={}
# 循环行列表数据
j = {}
d = {
'fenlei': 0,
'shop': 1,
'open': 2,
'id': 3,
'name': 4,
'item_url': 5,
'image': 6,
'price': 7,
'quan': 10,
'final_price': 11,
'start': 14,
'end': 15,
'link': 16
}
for r in xrange(1, nrows):
jinxuan = {}
for k, v in d.items():
col = table.cell(r, v).value
link = table.hyperlink_map.get((r, v))
# link=table.cell(r,c).Hyperlinks.Item(1).Address
print col, link.url_or_path if link else None
if k == 'fenlei':
simple = col.split('/', 1)[0]
if len(simple) > 4:
jinxuan.update({'simple': ''})
else:
jinxuan.update({'simple': simple})
if k == 'id':
id_col = col
jinxuan.update({k: link.url_or_path if link else col})
kw = {'timeout': 30, 'id': id_col}
request_url = 'https://detail.tmall.com/item.htm'
fenlei = j.get(jinxuan.get('fenlei'))
if fenlei:
shop = fenlei.get(jinxuan.get('shop'))
if shop:
shop_link = shop.get('url')
if not shop_link:
r = http('GET', request_url, headers, **kw)
# sel=Selector(text=r).xpath('/html/head/link[@rel="canonical"]/@href')
shop_link, shop_age = get_shop_parameter(
r, jinxuan.get('open'))
else:
shop_age = shop.get('age')
shop_list = shop.get('list')
if shop_list:
shop_list.append(jinxuan)
else:
shop_list = [jinxuan]
shop = {
'url': shop_link,
'open': jinxuan.get('open'),
'age': shop_age,
'list': shop_list
}
else:
r = http('GET', request_url, headers, **kw)
# sel=Selector(text=r).xpath('/html/head/link[@rel="canonical"]/@href')
shop_link, shop_age = get_shop_parameter(
r, jinxuan.get('open'))
shop = {
'list': [jinxuan],
'url': shop_link,
'open': jinxuan.get('open'),
'age': shop_age
}
fenlei.update({jinxuan.get('shop'): shop})
j.update({jinxuan.get('fenlei'): fenlei})
else:
# print jinxuan.get('item_url'),'-----------------------'
r = http('GET', request_url, headers, **kw)
# print r,'-----------------------'
# sel=Selector(text=r).xpath('/html/head/link[@rel="canonical"]/@href')
shop_link, shop_age = get_shop_parameter(r, jinxuan.get('open'))
j.update({
jinxuan.get('fenlei'): {
jinxuan.get('shop'): {
'list': [jinxuan],
'url': shop_link,
'age': shop_age,
'open': jinxuan.get('open')
}
}
})
json.dump(j, open('%s/%s' % (JINXUAN_DIR, 'jinxuan.json'), 'w'))
def send_blog(self,
blog_title,
blog_body,
blog_class,
tag,
vtoken,
blog_vote=None):
vote = {
'voteId': '',
'blogVote': 'yes',
'voteType': '1',
'voteTitle': '我 是 一 个 中 国 人 哈',
'voteData[]': '1111',
'voteData[]': '2222',
'voteData[]': '3333',
'voteData[]': '4444',
'voteData[]': '',
'rad': 'on',
'votePos': '0',
'voteYear': '2016',
'voteMonth': '8',
'voteDay': '5',
'voteHour': '10',
}
assoc = {
'assoc_article': '3d837c2c0102whmy,3d837c2c0100c4wm',
'assoc_style': '1',
'assoc_article_data': '',
}
kw = {
'ptype': '',
'teams': '',
'worldcuptags': '',
'album': '',
'album_cite': '',
'blog_id': '',
'is_album': '0',
'old365': '0',
'stag': '',
'sno': '',
'book_worksid': '',
'channel_id': '',
'url': '',
'channel': '',
'newsid': '',
'fromuid': '',
'wid': '',
'articletj': '',
'vtoken': 'vtoken',
'is_media': '0',
'is_stock': '0',
'is_tpl': '0',
'assoc_article': '',
'assoc_style': '1',
'assoc_article_data': '',
'article_BGM': '',
'xRankStatus': '',
'commentGlobalSwitch': '',
'commenthideGlobalSwitch': '',
'articleStatus_preview': '1',
'source': '',
'topic_id': '0',
'topic_channel': '0',
'topic_more': '',
'utf8': '1',
'conlen': '15',
'date_pub': '2016-06-04',
'time': '22:16:37',
'new_time': '',
'isTimed': '0',
'immediatepub': '0',
'blog_title': 'this is title9',
'blog_body': 'this is content9',
'blog_class': '2',
'tag': 'tag1,tag2,tag3,tag4,健康',
'x_cms_flag': '0',
'sina_sort_id': '117',
}
kw['blog_title'] = blog_title
kw['blog_body'] = blog_body
kw['blog_class'] = blog_class
kw['date_pub'] = datetime.datetime.now().strftime('%Y-%m-%d')
kw['time'] = datetime.datetime.now().strftime('%H:%M:%S')
kw['tag'] = tag
kw['vtoken'] = vtoken
try:
assoc_article = json.load(open(
'D:/mywork/tmall/assoc_user_%s.json' % u, 'r'),
strict=False)
except:
assoc_article = None
if assoc_article:
assoc['assoc_article'] = ','.join(assoc_article)
kw.update(**assoc)
if blog_vote:
kw.update(**blog_vote)
headers.update(
Referer=
'http://control.blog.sina.com.cn/admin/article/article_add.php')
result = http(
'POST',
'http://control.blog.sina.com.cn/admin/article/article_post.php',
headers, **kw)
default_logger.info(
'-----------------result-----------------------------------')
default_logger.info(result)
default_logger.info(
'----------------------------------------------------')
result = json.loads(result)
if result['code'] == 'B06001':
result_id = result['data']
if not assoc_article:
assoc_article = []
assoc_article.insert(0, result_id)
del assoc_article[10:]
json.dump(assoc_article,
open('D:/mywork/tmall/assoc_user_%s.json' % u, 'w'))