momoCrawler3.py 文件源码

def __init__(self, status):
        self.headers = {
            'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1700.107 Safari/537.36',
        }
        self.headers2 = {
            'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.106 Safari/537.36',
        }
        self.cookies = {
            '_ts_id': '999999999999999999',
        }
        self.cookies2 = {
            '_ts_id': '888888888888888888',
        }
        self.result_df = pd.DataFrame(columns=('GID', 'price', 'discount', 'payment_CreditCard', \
            'payment_Arrival', 'payment_ConvenienceStore', 'payment_ATM', 'payment_iBon', \
            'preferential_count', 'img_height', 'is_warm', 'is_cold', 'is_bright', 'is_dark', \
            '12H', 'shopcart', 'superstore', 'productFormatCount', 'attributesListArea', \
            'haveVideo', 'Taiwan','EUandUS','Germany','UK','US','Japan','Malaysia','Australia','other', \
            'supplementary', 'bottle', 'combination', 'look_times', 'label'))
        # outputOriginList = [u'??', u'??', u'??', u'??', u'??', u'??', u'????', u'??', u'??']
        if status == 'c':
            self.with_header = False
        elif status == 'i':
            self.with_header = True
        else:
            raise SystemInputError('???????: c -> ??, i -> ??????')

        jieba.set_dictionary('dict.txt.big')

    # ??