def parse(self, response):
#scrapy crawl collection145
url1 = 'http://www.wzmuseum.cn/Col/Col29/Index.aspx'
url2 = 'http://www.wzmuseum.cn/Col/Col30/Index.aspx'
url3 = 'http://www.wzmuseum.cn/Col/Col31/Index.aspx'
url4 = 'http://www.wzmuseum.cn/Col/Col32/Index.aspx'
url5 = 'http://www.wzmuseum.cn/Col/Col33/Index.aspx'
url6 = 'http://www.wzmuseum.cn/Col/Col34/Index.aspx'
url7 = 'http://www.wzmuseum.cn/Col/Col29/Index_2.aspx'
urlll = ('1', url1, url2, url3, url4, url5, url6, url7)
item = collectionItem()
a = (6, 2, 1, 1)
_list = response.xpath('/html/body/div[1]/div[4]/div[2]/div[2]/ul/li')
for li in _list:
coll_name = li.xpath('.//span/text()').extract_first()
#detail_url='http://www.westlakemuseum.com'+li.xpath('./td/a/@href').extract_first()
#coll_name=str.strip(coll_name)
coll_img = li.xpath('./a/@href').extract_first()
print(coll_name)
print(coll_img)
coll_desc = ''
if self.page_num <= 6:
new_url = (self.url % self.page_num)
print(new_url)
self.page_num += 1
yield scrapy.Request(new_url, callback=self.parse)
else:
if self.cnt <= 7:
new_url = urlll[self.cnt]
print(new_url)
self.cnt += 1
yield scrapy.Request(new_url, callback=self.parse)
def parse(self, response):
# //*[@id="building2"]/div/div[2]/table/tbody
coll_list = response.xpath('/html/body/div')
for li in coll_list:
item = collectionItem()
# if li.xpath('./td/a/text()').extract_first() != None:
# //*[@id="227613"]/text()
# coll_name = li.xpath('./td/a/text()').extract_first()
# # coll_name = ''.join(coll_name)
# print(coll_name)
# print(li.xpath('./td/a/@href').extract_first())
img_new = li.xpath('./section/div[1]/div/a/img/@src').extract_first()
img_new = img_new.replace(".",'',2)
img = "http://www.19371213.com.cn/collection" + img_new
print(img)
url_new = li.xpath('./section/div[1]/div/a/@href').extract_first()
url_new = url_new.replace(".",'',2)
detail_url = "http://www.19371213.com.cn/collection" + url_new
# detail_url = 'https://www.dpm.org.cn/' + li.xpath('./td/a/@href').extract_first()
item['museumID']=11
item['collectionImage']=img
yield scrapy.Request(detail_url,callback=self.parse_detail,meta={'item':item})
if self.page_num <= 17:
new_url = (self.url%self.page_num)
self.page_num += 1
yield scrapy.Request(new_url,callback=self.parse)
def parse(self, response):
item = collectionItem()
self.cnt += 1
if (self.cnt == 5):
self.urll = 'http://www.gthyjng.com/gcww/wwjs/krzzsq/'
if (self.cnt == 6):
self.urll = 'http://www.gthyjng.com/gcww/wwjs/jfzzsq/'
if (self.cnt == 7):
self.urll = 'http://www.gthyjng.com/gcww/wwjs/gjdww/'
urlll = ('1', '1',
'http://www.gthyjng.com/gcww/wwjs/tdgmsq/index_2.htm',
'http://www.gthyjng.com/gcww/wwjs/tdgmsq',
'http://www.gthyjng.com/gcww/wwjs/tdgmsq/index_3.htm',
'http://www.gthyjng.com/gcww/wwjs/krzzsq/',
'http://www.gthyjng.com/gcww/wwjs/jfzzsq/',
'http://www.gthyjng.com/gcww/wwjs/jfzzsq/index_1.htm',
'http://www.gthyjng.com/gcww/wwjs/gjdww/')
x = response.xpath('/html/body/div[4]/div/div[2]/div[2]/ul/li')
for li in x:
l1 = li.xpath('.//img/@src').extract_first()
l1 = l1[1:len(l1)]
coll_img = self.urll + l1
print(coll_img)
l1 = li.xpath('./a/@href').extract_first()
l1 = l1[1:len(l1)]
detail_url = self.urll + l1
print(detail_url)
print(self.cnt)
yield scrapy.Request(detail_url,
callback=self.parse_detail,
meta={'item': item})
if (self.cnt <= 7):
new_url = urlll[self.cnt + 1]
yield scrapy.Request(new_url, callback=self.parse)
def parse(self, response):
item = collectionItem()
coll_list = response.xpath(
'/html/body/div[2]/div[3]/div[2]/div[2]/ul/li')
for div in coll_list:
#/html/body/div[2]/div[3]/div[2]/div[2]/ul/li[1]/div[1]/span
coll_name = div.xpath('./div[1]/span/text()').extract_first()
print(coll_name)
coll_img = 'http:' + div.xpath(
'./div[2]/div[1]/a/img/@src').extract_first()
#/html/body/div[2]/div[3]/div[2]/div[2]/ul/li[4]/div[2]/div[1]/a/img
#http://services.ytta.cn
print(coll_img)
#/html/body/div[2]/div[3]/div[2]/div[2]/ul/li[1]/div[2]/div[1]/a
detail_url = 'http://www.ytmuseum.com' + div.xpath(
'./div[2]/div[1]/a/@href').extract_first()
yield scrapy.Request(detail_url,
callback=self.parse_detail,
meta={'item': item})
if self.page_num <= 8:
new_url = (self.url % self.page_num)
self.page_num += 1
yield scrapy.Request(new_url, callback=self.parse)
def parse2(self, response):
item = collectionItem()
a = (18, 1, 5, 1)
div_list = response.xpath(
'/html/body/div[1]/div[5]/div[3]/div[2]/ul/li')
for li in div_list:
coll_name = li.xpath('./div[2]/h3/a/text()').extract_first()
#print(coll_name)
x = li.xpath('./div[2]/p//text()').extract()
x = switch(x)
#x=ge(x)
#print(x)
coll_desc = x
if (len(x) > 100):
detail_url = 'http://www.81-china.com' + li.xpath(
'./div[2]/h3/a/@href').extract_first()
print(detail_url)
yield scrapy.Request(detail_url,
callback=self.parse_detail,
meta={'item': item})
coll_img = 'http://www.81-china.com' + li.xpath(
'.//img/@src').extract_first()
print(coll_name)
#print(coll_desc)
print(coll_img)
def parse(self, response):
# //*[@id="building2"]/div/div[2]/table/tbody
coll_list = response.xpath(
'//*[@id="app"]/div/div/div/div/main/ul/li[@class="col-list-i"]')
# print(coll_list)
for li in coll_list:
item = collectionItem()
# if li.xpath('./td/a/text()').extract_first() != None:
# //*[@id="227613"]/text()
coll_name = li.xpath('./a/h3/text()').extract_first()
# coll_name = ''.join(coll_name)
print(coll_name)
# print(li.xpath('./td/a/@href').extract_first())
detail_url = 'http://www.zhejiangmuseum.com' + li.xpath(
'./a/@href').extract_first()
img = li.xpath('./a/figure/img/@src').extract_first()
if img[0] == '/':
img = 'http://www.zhejiangmuseum.com' + img
print(img)
self.deep_urls.append(detail_url)
item['collectionName'] = coll_name
item['museumID'] = 5
item['collectionImage'] = img
yield scrapy.Request(detail_url,
callback=self.parse_detail,
meta={'item': item})
if self.page_num <= 291:
new_url = (self.url % self.page_num)
self.page_num += 1
self.new_urls.append(new_url)
yield scrapy.Request(new_url, callback=self.parse)
def parse(self, response):
#scrapy crawl collection148
item = collectionItem()
a=(126,35,5,3)
url1='https://www.chinasilkmuseum.com/zgxd/list_22.aspx?page=%d'
url2='https://www.chinasilkmuseum.com/xf/list_23.aspx?page=%d'
url3='https://www.chinasilkmuseum.com/mzx/list_24.aspx?page=%d'
urlll=('1',url1,url2,url3)
_list=response.xpath('/html/body/div[1]/div/div[8]/div/ul/li')
for li in _list:
coll_name=li.xpath('./p/a/text()').extract_first()
#detail_url='http://www.westlakemuseum.com'+li.xpath('./td/a/@href').extract_first()
coll_name=str.strip(coll_name)
coll_img='https://www.chinasilkmuseum.com'+li.xpath('./a/img/@src').extract_first()
print(coll_name)
print(coll_img)
detail_url='https://www.chinasilkmuseum.com'+li.xpath('./a/@href').extract_first()
#print((detail_url))
yield scrapy.Request(detail_url,callback=self.parse_detail,meta={'item':item})
if self.page_num <= a[self.cnt-1]:
new_url = (self.url%self.page_num)
print(new_url)
self.page_num += 1
yield scrapy.Request(new_url,callback=self.parse)
else :
if self.cnt<=3:
self.url=urlll[self.cnt]
self.cnt+=1
new_url=(self.url%1)
print(new_url)
self.page_num=2
yield scrapy.Request(new_url,callback=self.parse)
def parse(self, response):
# maxn = response.xpath('//*[@class="active"]/text()').extract_first()
# maxn = ''.join(maxn)
# maxn = int(maxn)
# //*[@id="building2"]/div/div[2]/table/tbody
# if maxn == '1':
# self.cot += 1
coll_list = response.xpath('//*[@id="articleListTable"]/ul/li')
for li in coll_list:
item = collectionItem()
# //*[@id="227613"]/text()
coll_name = li.xpath('./a/h5/text()').extract_first()
# coll_name = ''.join(coll_name)
print(coll_name)
# print(li.xpath('./td/a/@href').extract_first())
detail_url = 'http://www.chnmus.net' + li.xpath(
'./a/@href').extract_first()
coll_img = li.xpath('./a/img/@src').extract_first()
coll_img = 'http://www.chnmus.net' + coll_img
item['collectionName'] = coll_name
item['museumID'] = 9
item['collectionImage'] = coll_img
print(coll_img)
yield scrapy.Request(detail_url,
callback=self.parse_detail,
meta={'item': item})
if self.page_num <= 10:
# new_url = (self.url%(self.co_list[self.cot],self.page_num))
new_url = (self.url % self.page_num)
self.page_num += 1
yield scrapy.Request(new_url, callback=self.parse)
def parse(self, response):
item = collectionItem()
coll_list = response.xpath(
'/html/body/div[3]/div/div[2]/table[1]/tbody/tr/td/div/table/tbody/tr[1]/td'
)
coll_name = response.xpath(
'/html/body/div[3]/div/div[2]/table[1]/tbody/tr/td/div/table/tbody/tr[1]/td[1]/span/a/span/text()'
).extract_first()
print(coll_name)
#/html/body/div[3]/div/div[2]/table[1]/tbody/tr/td/div/table/tbody/tr[1]/td[1]
for div in coll_list:
coll_name = div.xpath('./span/a/span/text()').extract_first()
print(coll_name)
coll_img = div.xpath(
'./table/tbody/tr/td/a/img/@src').extract_first()
print(coll_img)
detail_url = div.xpath(
'./table/tbody/tr/td/a/@href').extract_first()
yield scrapy.Request(detail_url,
callback=self.parse_detail,
meta={'item': item})
if self.page_num <= 4:
new_url = (self.url % self.page_num)
self.page_num += 1
yield scrapy.Request(new_url, callback=self.parse)
def parse(self, response):
item = collectionItem()
coll_name = response.xpath(
'/html/body/table[3]/tbody/tr/td[3]/table/tbody/tr/td/table/tbody/tr[3]/td/ul/li[1]/a[1]/p//text()'
).extract()
coll_name = ''.join(coll_name)
print(coll_name)
def parse(self, response):
item = collectionItem()
coll_list = json.loads(response.text)["data"]["recordsList"]
for i in coll_list:
collectionName = i["name"]
collectionDescription = i["introduce"]
collectionImageUrl = i["picUrl"]
print((collectionName, collectionDescription, collectionImageUrl))
def parse_content(self, response):
item = collectionItem()
collectionImageUrl =response.urljoin(response.xpath("//div[@class='collectdetail clearfix ']//img/@src").get())
collectionName = response.xpath(
"//h1/text()").get()
collectionDescription = "".join("".join(response.xpath(
"//div[@class='cont']/p/text()").getall()).split())
print((collectionName, collectionImageUrl, collectionDescription))
def parse(self, response):
item = collectionItem()
coll_list = json.loads(response.text)["body"]["list"]
for i in coll_list:
collectionName = i["title"]
collectionDescription = i["description"]
collectionImageUrl = i["litPic"]
print((collectionName, collectionDescription, collectionImageUrl))
def parse(self, response):
item = collectionItem()
coll_list = json.loads(response.text)["data"]
for i in coll_list:
collectionName = i["title"]
collectionDescription = i["texture"]
collectionImageUrl = "https://www.gzchenjiaci.com" + i["imgurl"]
print((collectionName, collectionDescription, collectionImageUrl))
def parse(self, response):
item = collectionItem()
coll_list = json.loads(response.text)["data"]["records"]
for i in coll_list:
coll_name = i["exhibitName"]
coll_desc = i["description"]
#coll_img = i[""]
print((coll_name, coll_desc))
def parse_content(self, response):
item = collectionItem()
collectionName = response.xpath("//h1[2]").get()
collectionDescription = "".join("".join(
response.xpath('//span[@style]/text()').getall()).split())
collectionImageUrl = response.xpath(
'//div[@class="newsxx_nr"]//img/@src').get()
print((collectionName, collectionImageUrl, collectionDescription))
def parse_content(self, response):
item = collectionItem()
collectionName = response.xpath("//h2/text()").get()
collectionDescription = "".join("".join(
response.xpath(
'//div[@class="neirong"]/p/text()').getall()).split())
collectionImageUrl = "http://www.gxmuseum.cn" + response.xpath(
'//div[@class="neirong"]//img/@src').get()
print((collectionName, collectionImageUrl, collectionDescription))
def parse(self, response):
item = collectionItem()
coll_list = json.loads(response.text)["Rows"]
for i in coll_list:
coll_name = i["Title"]
coll_desc = i["Contents"]
#coll_img = i[""]
print(coll_name)
print(coll_desc)
def parse(self, response):
item = collectionItem()
li_list = json.loads(response.text)['data']
for li in li_list:
collectionName = li['name']
# print(collectionName)
collectionIntroduction = li['introduce']
# print(collectionIntroduction)
collectionImage = li['imgPath']
def parse_content(self, response):
item = collectionItem()
collectionImageUrl = "http://www.sunyat-sen.org" + response.xpath(
"//div[@class='zwpic']/img/@src").get()
collectionName = response.xpath("//h3/text()").get()
collectionDescription = "".join("".join(
response.xpath(
"//div[@class='contentBox']//text()").getall()).split())
print((collectionName, collectionImageUrl, collectionDescription))
def parse_content(self, response):
item = collectionItem()
collectionImageUrl = response.meta['img']
collectionName = response.xpath(
"//div[@class='titleBox']/p/text()").get()
collectionDescription = "".join("".join(
response.xpath(
"//div[@class='textBox']//text()").getall()).split())
print((collectionName, collectionImageUrl, collectionDescription))
def parse(self, response):
item = collectionItem()
coll_list = json.loads(response.text)["data"]
for i in coll_list:
coll_name = i["collectionName"]
#coll_desc = i["mipOpenCulturalrelicInfo"]["collectionsCategory"]
coll_img = i["picUrl"]
print(coll_name)
print(coll_img)
def parse(self, response):
item = collectionItem()
coll_list = response.xpath('/html/body/div[5]/div/div/div[2]/div')
for div in coll_list:
#detail_url = '1'
if div.xpath('./a/@href'):
detail_url = 'http://www.qdyzyzmuseum.com' + div.xpath('./a/@href').extract_first()
yield scrapy.Request(detail_url,callback=self.parse_detail,meta={'item':item})
def parse_content(self, response):
item = collectionItem()
collectionImageUrl = "https://www.jc-museum.cn" + \
response.xpath("//div[@class='box2 wf100']/img/@src").get()
collectionName = response.xpath(
"//div[@class='box1 wf100']/span/text()").get()
description = "".join("".join(response.xpath(
"//div[@class='box2 wf100']//text()").getall()).split())
print((collectionName, collectionImageUrl, description))
def parse(self, response):
item = collectionItem()
coll_list = json.loads(response.text)["data"]["data"]
for i in coll_list:
collectionName = i["mingchen"]
collectionDescription = i["niandai"] + " " + i["leibie"] + " " + i[
"chicun"] + " " + i["baocun_zhuangtai"]
collectionImageUrl = "http://www.hainanmuseum.org/cms/1/image/public/wenwu/" + i[
"pics"][0] + ".png"
print((collectionName, collectionDescription, collectionImageUrl))
def content_parse(self, response):
item = collectionItem()
doc = response.xpath("//div[@class='zhanlan-pic']")
collectionName = doc.xpath(
"./div[@class='list-right-bt']/text()").get()
collectionImageUrl = "http://www.hylae.com" + doc.xpath(
".//img/@src").get()
collectionDescription = "".join("".join(
doc.xpath(".//p//text()").getall()).split()) #去除\xa0字符
print((collectionName, collectionImageUrl, collectionDescription))
def parse(self, response):
item = collectionItem()
coll_list = json.loads(response.text)["data"]
for i in coll_list:
collectionName = i["Title"]
contentHTML = i["Contents"]
Selector = etree.HTML(contentHTML)
collectionDescription = "".join(Selector.xpath("//p/text()"))
collectionImageUrl = Selector.xpath("//img/@src")[0]
print((collectionName, collectionDescription, collectionImageUrl))
def parse_content(self, response):
item = collectionItem()
collectionImageUrl = "http://www.ynmuseum.org" + \
response.xpath(
"//div[@class='yc_info']/img/@src").get()
collectionDescription = "".join("".join(
response.xpath(
"//div[@class='yc_infoCon']/p//text()").getall()).split())
collectionName = collectionDescription.split("》")[0] + "》"
print((collectionName, collectionImageUrl, collectionDescription))
def parse(self, response):
item = collectionItem()
url_list = response.xpath(
"//ul[@class='prod_list cf']/li/a/@href").getall()
for i in url_list:
yield scrapy.Request("http://www.ynmuseum.org" + i,
callback=self.parse_content)
next_page = response.xpath(
"//div[@class='page_w']/a[@class='next']/@href").get()
if next_page != None:
yield scrapy.Request("http://www.ynmuseum.org" + next_page)
def parse(self, response):
item = collectionItem()
doc = response.xpath("//div[@class='list-right']")
educationName = doc.xpath(
".//div[@class='list-right-bt']/text()").get()
educationImageUrl = "http://www.hylae.com" + doc.xpath(
".//img/@src").get(
default="/upfile/2019/07/20190731171111_475.jpg")
educationDescription = "".join("".join(
doc.xpath(".//p//text()").getall()).split()) #去除\xa0字符
print((educationName, educationImageUrl, educationDescription))
