def parse(self, response):
item = MuseumsItem()
item["museumID"] = 120
item["museumName"] = '西安博物院'
item["Location"] = '陕西省西安市南门外友谊西路'
#item["Location"] = str(item["Location"]).replace(u'\\xa0', u' ')
#item["Location"] = str(item["Location"]).replace(u'\xa0', u' ')
item["Link"] = 'http://www.xabwy.com'
item["opentime"] = response.xpath(
'normalize-space(/html//div[4]/div[2]/div[2]/text()[1])'
).extract_first()
item["opentime"] = str(item["opentime"]).replace(u'\\xa0', u' ')
item["opentime"] = str(item["opentime"]).replace(u'\xa0', u' ')
item["telephone"] = response.xpath(
'normalize-space(/html//div[4]/div[2]/div[2]/text()[2])'
).extract_first()
item["telephone"] = str(item["telephone"]).replace(u'\\xa0', u' ')
item["telephone"] = str(item["telephone"]).replace(u'\xa0', u' ')
url = 'http://www.xabwy.com/Statics/2020.01/66.html'
# 处理详情页
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item": item} #传递参数
)
def parse(self, response):
item = MuseumsItem()
item["museumID"] = 107
item["museumName"] = '遵义会议纪念馆'
item["Location"] = response.xpath(
'/html//div[4]/div[2]/div/div[1]/div/div[2]/div[3]/div[1]/text()'
).extract_first()
item["Location"] = str(item["Location"]).replace(u'\\xa0', u'')
item["Location"] = str(item["Location"]).replace(u'\xa0', u'')
item["Link"] = 'http://www.zunyihy.cn/'
item["opentime"] = response.xpath(
'normalize-space(/html//div[4]/div[2]/div/div[1]/div/div[2]/div[2])'
).extract_first()
item["opentime"] = str(item["opentime"]).replace(u'\\xa0', u'')
item["opentime"] = str(item["opentime"]).replace(u'\xa0', u'')
item["telephone"] = response.xpath(
'/html/body/div[4]/div[2]/div/div[1]/div/div[2]/div[3]/div[3]/text()'
).extract_first()
item["telephone"] = str(item["telephone"]).replace(u'\\xa0', u'')
item["telephone"] = str(item["telephone"]).replace(u'\xa0', u'')
url = 'http://www.zunyihy.cn/about.html#about2'
# 处理详情页
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item": item} #传递参数
)
def parse(self, response):
item = MuseumsItem()
item["museumID"] = 122
item["museumName"] = '大唐西市博物馆'
item["Location"] = response.xpath(
'normalize-space(/html/body/div/form/div[4]/div[2]/div[2]/p[5]/span)'
).extract_first()
item["Location"] = str(item["Location"]).replace(u'\\xa0', u' ')
item["Location"] = str(item["Location"]).replace(u'\xa0', u' ')
item["Link"] = 'http://www.dtxsmuseum.com/'
item[
"opentime"] = '全年开放（每周一及除夕闭馆，法定节假日正常开放），夏季：9：00-17：30（16：30停止票务办理），冬季：9：00-17：00（16:：0停止票务办理）'
#item["opentime"] = str(item["opentime"]).replace(u'\\xa0', u' ')
#item["opentime"] = str(item["opentime"]).replace(u'\xa0', u' ')
item["telephone"] = response.xpath(
'normalize-space(/html/body/div/form/div[4]/div[2]/div[2]/p[9]/span)'
).extract_first()
item["telephone"] = str(item["telephone"]).replace(u'\\xa0', u' ')
item["telephone"] = str(item["telephone"]).replace(u'\xa0', u' ')
url = 'http://www.dtxsmuseum.com/news_show.aspx?id=1'
# 处理详情页
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item": item} #传递参数
)
def parse(self, response):
item = MuseumsItem()
item["museumID"] = 111
item["museumName"] = '重庆红岩历史博物馆'
item["Location"] = '重庆市渝中区红岩村52号'
item["Link"] = 'http://www.hongyan.info/'
item["opentime"] = '1月1日-12月31日 09:00-17:00'
item["telephone"] = '023-63300192 63303065'
url = 'http://www.hongyan.info/'
# 处理详情页
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item": item} #传递参数
)
def parse(self, response):
item=MuseumsItem()
item["museumID"]=119
item["museumName"]='西安半坡博物馆'
item["Location"]='西安市半坡路155号'
item["Link"]='http://www.banpomuseum.com.cn/'
item["opentime"]='旺季：（3月1日-11月30日）8:00----17:30 淡季：（12月1日-2月底）8:00----17:00'
item["telephone"]='联系电话：029-62815385 投诉电话：18729251954'
url='http://www.banpomuseum.com.cn/'
# 处理详情页
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item":item}#传递参数
)
def parse(self, response):
item = MuseumsItem()
item["museumID"] = 113
item["museumName"] = '西藏博物馆'
item["Location"] = '西藏自治区拉萨市城关区民族南路2号'
item["Link"] = 'http://www.tibetmuseum.com.cn'
item[
"opentime"] = '夏秋季(5月1日至10月31日):09:30-17:30 (17:00游客停止入场)冬春季(11月1日至次年4月30日):10:30-17:00(16:30游客停止入场)'
item["telephone"] = '0891-6835244 0891-6812210'
url = 'http://www.tibetmuseum.com.cn/zh-CN/brief/historyRecord?isNav=yes&navIndex=1'
# 处理详情页
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item": item} #传递参数
)
def parse(self, response):
item = MuseumsItem()
item["museumID"] = 105
item["museumName"] = '成都金沙遗址博物馆'
item["Location"] = '四川省成都市青羊区金沙遗址路2号'
item["Link"] = 'http://www.jinshasitemuseum.com/'
item[
"opentime"] = '夏令时8:30-20:00；冬令时8:30-18:30；周一闭馆' #response.xpath("/html/body/div[1]/section/footer/div[1]/div/text()[2]").extract_first()
item["telephone"] = response.xpath(
"/html/body/div[4]/div[1]/div[1]/div/a[5]/text()").extract_first()
url = 'http://www.jinshasitemuseum.com/About/Introduction'
# 处理详情页
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item": item} #传递参数
)
def parse(self, response):
item = MuseumsItem()
item["museumID"] = 117
item["museumName"] = '汉阳陵博物馆'
item["Location"] = '地址：西安咸阳国际机场专线公路东段'
item["Link"] = 'http://www.hylae.com/'
item["opentime"] = response.xpath(
"normalize-space(/html/body/div[3]/div[2]/div[2]/div/div[1]/div[2]/text()[1])"
).extract_first()
item["telephone"] = '029-62657569'
url = 'http://www.hylae.com/index.php?ac=article&at=list&tid=10'
# 处理详情页
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item": item} #传递参数
)
def parse(self, response):
item = MuseumsItem()
item["museumID"] = 114
item["museumName"] = '陕西历史博物馆'
item["Location"] = response.xpath(
"/html/body/div[3]/div/div[2]/p[3]/text()").extract_first()
item["Link"] = 'http://www.sxhm.com/'
item["opentime"] = '周二至周日 09:00-17:30；遇法定节假日周一除外'
item["telephone"] = response.xpath(
"/html/body/div[3]/div/div[2]/p[1]/text()").extract_first()
url = 'http://www.sxhm.com/index.php?ac=article&at=list&tid=230'
# 处理详情页
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item": item} #传递参数
)
def parse(self, response):
item = MuseumsItem()
item["museumID"] = 115
item["museumName"] = '秦始皇帝陵兵马俑博物馆'
item["Location"] = '河南省郑州市金水区农业路8号'
item["Link"] = 'http://bmy.com.cn/'
item["opentime"] = response.xpath(
"/html/body/div[4]/div[1]/div[3]/div/div[2]/div[2]/text()"
).extract_first()
item["telephone"] = response.xpath(
"/html/body/div[3]/div/div/div[2]/p/span/text()").extract_first()
url = 'http://www.bmy.com.cn/html/gov/jggk/8eaf8a3015b643b7adcb9d6815e0f845.html'
# 处理详情页
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item": item} #传递参数
)
def parse(self, response):
item=MuseumsItem()
item["museumID"]=106
item["museumName"]='自贡市盐业历史博物馆'
item["Location"]=response.xpath("normalize-space(/html/body/div[6]/div/div[2]/p[1])").extract_first()
item["Location"] = str(item["Location"]).replace(u'\u3000', u'')
item["Link"]='http://www.zgshm.cn/index.html'
item["opentime"]='1月1日-12月31日 08:30-16:30'
item["telephone"]=response.xpath("normalize-space(/html/body/div[6]/div/div[2]/p[2]/text())").extract_first()
item["telephone"] = str(item["telephone"]).replace(u'\u3000', u' ')
url='http://www.zgshm.cn/content.jsp?id=297e0fc26362ffbb016380a82d360199'# +response.xpath("/html/body/div[1]/ul//a/@href").extract_first()
# 处理详情页r
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item":item}#传递参数
)
def parse(self, response):
item = MuseumsItem()
item["museumID"] = 110
item["museumName"] = '重庆中国三峡博物馆'
item["Location"] = response.xpath(
"/html//div/div/div[5]/div[2]/div[2]/div/div[2]/ul/li[5]/p/text()"
).extract_first()
item["Link"] = 'http://www.3gmuseum.cn/'
item["opentime"] = '每日9:00-17:00（16:00禁止入馆） 周一闭馆（法定节假日除外）'
item["telephone"] = response.xpath(
"/html//div/div/div[5]/div[2]/div[2]/div/div[2]/ul/li[1]/p/text()"
).extract_first()
url = 'http://www.3gmuseum.cn/web/article/toArticleNo.do?articleno=1&base=&fullPath=http%3A%2F%2Fwww.3gmuseum.cn&type=&itemsonno=12121212&topitemno=402880b25a3bb962015a3bc512212223&itemno=402880b25a3bb962015a3bc512212223'
# 处理详情页
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item": item} #传递参数
)
def parse(self, response):
item = MuseumsItem()
item["museumID"] = 116
item["museumName"] = '延安革命纪念馆'
item["Location"] = response.xpath(
"/html/body/div[2]/div[2]/div[2]/div/div[2]/p[2]/span/strong"
).extract_first()
item["Link"] = 'http://www.yagmjng.com/'
item["opentime"] = '每日09：00至17：00（16：00停止入馆）'
item["telephone"] = response.xpath(
"/html/body/div[2]/div[2]/div[2]/div/div[2]/p[4]/span/strong/text()"
).extract_first()
url = 'http://www.yagmjng.com/rsf/site/jinianguan/zhanguanjianjie/info/2020/81013.html'
# 处理详情页
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item": item} #传递参数
)
def parse(self, response):
item = MuseumsItem()
item["museumID"] = 112
item["museumName"] = '重庆自然博物馆'
item["Location"] = response.xpath(
'normalize-space(//div[3]/div[5]//div[3]/div[1]/text())'
).extract_first()
item["Link"] = 'https://www.cmnh.org.cn/'
item["opentime"] = response.xpath(
'//div[3]/div[1]//div[3]//div[1]/p[1]/text()[3]').extract_first()
item["telephone"] = response.xpath(
'normalize-space(//div/div[3]/div[5]//div[3]/h3)').extract_first()
url = 'https://www.cmnh.org.cn/about/?4.html'
# 处理详情页
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item": item} #传递参数
)
def parse(self, response):
item = MuseumsItem()
item["museumID"] = 108
item["museumName"] = '云南省博物馆'
item["Location"] = '云南省昆明市广福路6393号'
item["Link"] = 'http://www.ynmuse um.org'
item["opentime"] = response.xpath(
"/html/body/div/div[3]/div[2]/div/div[1]/div/div[3]/div/text()"
).extract_first()
item["telephone"] = response.xpath(
"/html//div/div[3]/div[2]/div/div[1]/div/div[3]/div/text()"
).extract_first()
url = 'http://www.ynmuseum.org' + response.xpath(
"//div/div[1]/div/ul/li/div/div/div/a/@href").extract_first()
# 处理详情页
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item": item} #传递参数
)
def parse(self, response):
item = MuseumsItem()
item["museumID"] = 128
item["museumName"] = '青海省博物馆'
item["Location"] = '青海省西宁市西关大街58号'
#item["Location"] = str(item["Location"]).replace(u'\\xa0', u' ')
#item["Location"] = str(item["Location"]).replace(u'\xa0', u' ')
item["Link"] = 'http://www.qhmuseum.cn/'
item["opentime"] = '夏季：9:00—16:30；冬季：9:30—16:00，每周一闭馆休整。'
#item["opentime"] = str(item["opentime"]).replace(u'\\xa0', u' ')
#item["opentime"] = str(item["opentime"]).replace(u'\xa0', u' ')
item["telephone"] = '0971--6118691'
#item["telephone"] = str(item["telephone"]).replace(u'\\xa0', u' ')
#item["telephone"] = str(item["telephone"]).replace(u'\xa0', u' ')
url = 'https://baike.baidu.com/item/%E9%9D%92%E6%B5%B7%E7%9C%81%E5%8D%9A%E7%89%A9%E9%A6%86/1627225?fr=aladdin'
# 处理详情页
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item": item} #传递参数
)
def parse(self, response):
item=MuseumsItem()
item["museumID"]=126
item["museumName"] ='宁夏固原博物馆'
item["Location"] = response.xpath('normalize-space(/html//div[3]/div/div[2]/p[2]/text())').extract_first()
item["Location"] = str(item["Location"]).replace(u'\\xa0', u'')
item["Location"] = str(item["Location"]).replace(u'\xa0', u'')
item["Link"]='http://www.nxgybwg.com/'
item["opentime"] = response.xpath('normalize-space(/html//div[2]/div/div[7]/div/div/div[1]/div/div[1]/p/text()[2])').extract_first()
item["opentime"] = str(item["opentime"]).replace(u'\\xa0', u'')
item["opentime"] = str(item["opentime"]).replace(u'\xa0', u'')
item["telephone"]=response.xpath('normalize-space(/html//div[3]/div/div[2]/p[3]/text())').extract_first()
item["telephone"] = str(item["telephone"]).replace(u'\\xa0', u'')
item["telephone"] = str(item["telephone"]).replace(u'\xa0', u'')
url='http://www.nxgybwg.com/e/action/ShowInfo.php?classid=1&id=307'
# 处理详情页
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item":item}#传递参数
)
def parse(self, response):
item=MuseumsItem()
item["museumID"]=123
item["museumName"] ='甘肃省博物馆'
item["Location"] ='甘肃省兰州市七里河区西津西路3'
#item["Location"] = str(item["Location"]).replace(u'\\xa0', u' ')
#item["Location"] = str(item["Location"]).replace(u'\xa0', u' ')
item["Link"]='http://www.gansumuseum.com/'
item["opentime"] = response.xpath('/html/body/div[1]/div[1]/div[2]/div/ul/li[3]/text()').extract_first()
item["opentime"] = str(item["opentime"]).replace(u'\\xa0', u' ')
item["opentime"] = str(item["opentime"]).replace(u'\xa0', u' ')
item["telephone"]='0931-2346308'
#item["telephone"] = str(item["telephone"]).replace(u'\\xa0', u' ')
#item["telephone"] = str(item["telephone"]).replace(u'\xa0', u' ')
url='http://www.gansumuseum.com/about/show-1.html'
# 处理详情页
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item":item}#传递参数
)
def parse(self, response):
item=MuseumsItem()
item["museumID"]=121
item["museumName"] ='宝鸡青铜器博物院'
item["Location"] =response.xpath('normalize-space(/html/body/div[3]/div/div[2]/text()[4])').extract_first()
item["Location"] = str(item["Location"]).replace(u'\\xa0', u' ')
item["Location"] = str(item["Location"]).replace(u'\xa0', u' ')
item["Link"]='http://www.bjqtm.com/'
item["opentime"] = response.xpath('/html/body/div[1]/div[2]/div[1]/p[1]/text()[1]').extract_first()
#item["opentime"] = str(item["opentime"]).replace(u'\\xa0', u' ')
#item["opentime"] = str(item["opentime"]).replace(u'\xa0', u' ')
item["telephone"]=response.xpath('normalize-space(/html/body/div[1]/div[2]/div[1]/p[2])').extract_first()
item["telephone"] = str(item["telephone"]).replace(u'\\xa0', u' ')
item["telephone"] = str(item["telephone"]).replace(u'\xa0', u' ')
url='http://www.bjqtm.com/index.php?ac=article&at=list&tid=44'
# 处理详情页
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item":item}#传递参数
)
def parse(self, response):
item = MuseumsItem()
item["museumID"] = 130
item["museumName"] = '吐鲁番博物馆'
item["Location"] = '吐鲁番市高昌区木纳尔路1268号'
#item["Location"] = str(item["Location"]).replace(u'\\xa0', u' ')
#item["Location"] = str(item["Location"]).replace(u'\xa0', u' ')
item["Link"] = ''
item["opentime"] = '周二至周日10:00-18:00'
#item["opentime"] = str(item["opentime"]).replace(u'\\xa0', u' ')
#item["opentime"] = str(item["opentime"]).replace(u'\xa0', u' ')
item["telephone"] = '0995-7619644;0995-7619645;0995-7619650'
#item["telephone"] = str(item["telephone"]).replace(u'\\xa0', u' ')
#item["telephone"] = str(item["telephone"]).replace(u'\xa0', u' ')
url = 'http://www.xabwy.com/Statics/2020.01/66.html'
# 处理详情页
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item": item} #传递参数
)
def parse(self, response):
item = MuseumsItem()
item["museumID"] = 124
item["museumName"] = '天水市博物馆'
item["Location"] = '甘肃省天水市秦州区伏羲路110号'
#item["Location"] = str(item["Location"]).replace(u'\\xa0', u' ')
#item["Location"] = str(item["Location"]).replace(u'\xa0', u' ')
item["Link"] = 'http://www.tssbwg.com.cn/'
item["opentime"] = '每天上午8:00 - 12:00；下午 14:00 - 18:00 开放'
#item["opentime"] = str(item["opentime"]).replace(u'\\xa0', u' ')
#item["opentime"] = str(item["opentime"]).replace(u'\xa0', u' ')
item["telephone"] = '0938-8291377'
#item["telephone"] = str(item["telephone"]).replace(u'\\xa0', u' ')
#item["telephone"] = str(item["telephone"]).replace(u'\xa0', u' ')
url = 'http://www.tssbwg.com.cn/html/2013/zzjg_1127/218.html'
# 处理详情页
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item": item} #传递参数
)
def parse(self, response):
item = MuseumsItem()
item["museumID"] = 125
item["museumName"] = '敦煌研究院'
item["Location"] = '甘肃省酒泉市敦煌市'
#item["Location"] = str(item["Location"]).replace(u'\\xa0', u' ')
#item["Location"] = str(item["Location"]).replace(u'\xa0', u' ')
item["Link"] = 'https://www.dha.ac.cn/'
item["opentime"] = ''
#item["opentime"] = str(item["opentime"]).replace(u'\\xa0', u' ')
#item["opentime"] = str(item["opentime"]).replace(u'\xa0', u' ')
item["telephone"] = '敦煌研究院网络中心 : 0937-8869123'
#item["telephone"] = str(item["telephone"]).replace(u'\\xa0', u' ')
#item["telephone"] = str(item["telephone"]).replace(u'\xa0', u' ')
url = 'https://www.dha.ac.cn/'
# 处理详情页
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item": item} #传递参数
)
def parse(self, response):
item = MuseumsItem()
item["museumID"] = 109
item["museumName"] = '云南名族博物馆'
item["Location"] = response.xpath('normalize-space(/html//div/div/div/div/div[2]/div/div[1]/div[2]/div/div/div[2]/div/div[1]/div[2]/div/div/p[1])').extract_first()
item["Location"] = str(item["Location"]).replace(u'\\xa0', u' ')
item["Location"] = str(item["Location"]).replace(u'\xa0', u' ')
item["Link"] = 'http://www.ynnmuseum.com/main.html'
item["opentime"] = '开放时间：周二至周日上午9:00——下午4:30（周一闭馆）'
item["telephone"] = response.xpath(
'normalize-space(/html//div/div/div/div/div[2]/div/div[1]/div[2]/div/div/div[2]/div/div[1]/div[2]/div/div/p[3])').extract_first()
item["telephone"] = str(item["telephone"]).replace(u'\\xa0', u' ')
item["telephone"] = str(item["telephone"]).replace(u'\xa0', u' ')
url = 'http://www.ynnmuseum.com/abouts.html'
# 处理详情页
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item": item} # 传递参数
)
def parse(self, response):
item = MuseumsItem()
item["museumID"] = 129
item["museumName"] = '新疆维吾尔自治区博物馆'
item["Location"] = '乌鲁木齐市沙依巴克区西北路581号'
#item["Location"] = str(item["Location"]).replace(u'\\xa0', u' ')
#item["Location"] = str(item["Location"]).replace(u'\xa0', u' ')
item["Link"] = ''
#item["opentime"] = response.xpath('normalize-space(/html/body/div[4]/div[2]/div[2]/text()[1])').extract_first()
#item["opentime"] = str(item["opentime"]).replace(u'\\xa0', u' ')
item["opentime"] = '每周二至周日的10：30—18：00'
item["telephone"] = '0991-4536436'
#item["telephone"] = str(item["telephone"]).replace(u'\\xa0', u' ')
#item["telephone"] = str(item["telephone"]).replace(u'\xa0', u' ')
url = 'http://www.xabwy.com/Statics/2020.01/66.html'
# 处理详情页
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item": item} #传递参数
)
def parse(self, response):
item=MuseumsItem()
item["museumID"]=118
item["museumName"]='西安碑林博物馆'
item["Location"]='西安三学街15号'
item["Link"]='http://www.beilin-museum.com/'
content=""
x = response.xpath("//table[4]//table[2]//td[3]/table[3]//div[3]/p[2]/text()[1]").extract_first()
content += x
x = response.xpath("//table[4]//table[2]//td[3]/table[3]//div[3]/p[2]/text()[2]").extract_first()
content += x
x = response.xpath("//table[4]//table[2]//td[3]/table[3]//div[3]/p[2]/text()[3]").extract_first()
content += x
item["opentime"]=content.replace(u'\xa0', u'')
item["telephone"]='87210764'
url='http://www.beilin-museum.com/contents/45/976.html'
# 处理详情页
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item":item}#传递参数
)
def parse(self, response):
item = MuseumsItem()
item["museumID"] = 127
item["museumName"] = '宁夏回族自治区博物馆'
item["Location"] = response.xpath(
'normalize-space(/html//footer/div/div[2]/div/div[1]/span[3])'
).extract_first()
item["Location"] = str(item["Location"]).replace(u'\\xa0', u' ')
item["Location"] = str(item["Location"]).replace(u'\xa0', u' ')
item["Link"] = 'https://www.nxbwg.com/'
item["opentime"] = '周一闭馆,周二-周日:9:00-16:50'
#item["opentime"] = str(item["opentime"]).replace(u'\\xa0', u' ')
#item["opentime"] = str(item["opentime"]).replace(u'\xa0', u' ')
item["telephone"] = '电话：(0951)5085093'
#item["telephone"] = str(item["telephone"]).replace(u'\\xa0', u' ')
#item["telephone"] = str(item["telephone"]).replace(u'\xa0', u' ')
url = 'https://www.nxbwg.com/a/30.html'
# 处理详情页
yield scrapy.Request(
url,
callback=self.parse_detail,
meta={"item": item} #传递参数
)
