def parse_start_url(self, response):
print('request_url= ', response.request.url)
li = response.xpath('//ul[@class="newslist"]//a')
for a in li:
item = BiddinginfospiderItem()
title = a.xpath("..//h1").xpath('normalize-space(string(.))').get()
href = a.xpath('.//@href').get()
code = a.xpath(
'.//ul[@class="newsinfo"]//li[1]//span//text()').get()
t = a.xpath('.//div[@class="newsDate"]').xpath(
'normalize-space(string(.))').get()
if t:
t = t.replace(" ", "").replace("/", "-")
ctime = t[:3] + "-" + t[4:]
item.update(
code=code,
industry=self.industry,
category=self.category,
title=title,
ctime=ctime,
href=href,
)
# print(item)
yield item
def parse_start_url(self, response):
print('request_url= ', response.request.url)
body = json.loads(str(response.body, "utf-8"))
li = body.get("obj")
print(len(li))
for l in li:
item = BiddinginfospiderItem()
title = l.get("PROJECTNAME")
ctime = l.get("RECEIVETIME")
category = l.get("TABLENAME")
code = l.get("PROJECTCODE")
url = l.get("URL", "") + "&id="
id = l.get("ID", "")
href = response.urljoin("?getNoticeDetail&url=" + url + id)
print(href)
item.update(
category=self.category_dict[category],
title=title,
ctime=ctime,
href=href,
code=code
)
# yield scrapy.Request(method="GET", url=href, dont_filter=True, callback=self.parse_item,
# meta={'item': item})
yield item
def parse_page(self, response):
if not response:
return BiddinginfospiderItem()
print('request_url= ', response.request.url)
body = json.loads(str(response.body, "utf-8"))
li = body.get("data")
print("Num :", len(li))
for l in li:
item = BiddinginfospiderItem()
sheng = l.get('districtShow')
shiQu = l.get('platformName')
shi = self.getSHI(shiQu)
href = l.get("url"),
if isinstance(href, tuple):
href = href[0]
print("href is,", href)
# href = href.replace("a", "b")
item.update(
city=sheng + "-" + shi if shi else sheng,
title=l.get("title"),
ctime=l.get("timeShow"),
category=l.get("classifyShow"),
href=href,
industry=l.get("tradeShow"),
)
print("ITEM IS")
# print(item)
yield item
def parse(self, response):
for i in range(1, self.endPageNum):
form_data = {
"page.currentPage": str(i),
"page.perPageSize": "20",
"noticeBean.companyName": "",
"noticeBean.title": "",
"noticeBean.startDate": "",
"noticeBean.endDate": "",
}
response = requests.post(self.tmpl_url,
headers=self.headers,
data=form_data)
res = scrapy.Selector(text=response.text)
li = res.xpath('//table[@class="jtgs_table"]//tr')
article_tmp_url = 'https://b2b.10086.cn/b2b/main/viewNoticeContent.html?noticeBean.id={0}'
for l in li[1:]:
item = BiddinginfospiderItem()
a = l.xpath(".//a")
id = l.xpath('@onclick').get()[14:-2]
href = article_tmp_url.format(id)
title = a.xpath('.//text()').get()
item.update(
title=title,
href=href,
)
yield item
def parse_page(self, response):
li_lst = response.xpath('//div[@class="filter-content"]/ul/li')
for l in li_lst:
item = BiddinginfospiderItem()
a = l.xpath('./a')
title = a.xpath('.//@title').extract_first()
href = response.urljoin(a.xpath('.//@href').extract_first())
ctime = self.get_ctime(a.xpath('.//span[@class="time"]//text()'))
item.update(
title=title,
ctime=ctime,
href=href,
)
yield item
def parse_page(self, response):
res = scrapy.Selector(response)
li = res.xpath('//div[@class="titlecss"]')
for l in li:
item = BiddinginfospiderItem()
a = l.xpath(".//a")
title = a.xpath('.//@title').get()
href = response.urljoin(a.xpath('.//@href').get())
ctime = self.get_ctime(l.xpath('../following-sibling::td[1]//text()'))
item.update(
title=title,
href=href,
ctime=ctime,
)
# print(item)
yield item
def parse_shangdong_xml(self, response):
# response已经完成返回xml的解析
# datastore = etree.XML(response.text)
html = ''.join(response.xpath('//record/text()').extract())
# 产生内容页的请求
for li in etree.HTML(html).xpath('//li'):
item = BiddinginfospiderItem()
a = li.xpath(".//a")[0]
item['href'] = a.xpath(".//@href")[0]
item['title'] = a.xpath(".//text()")[0]
item['ctime'] = li.xpath('.//span//text()')[0]
# print(item)
yield item
# 如果是全部爬取则继续获取下一页
if not self.biddingInfo_update:
selector = etree.XML(response.body)
a = [0]
next_select = selector.xpath('//nextgroup/text()')
if next_select:
a = next_select[0]
href = etree.HTML(a).xpath('//a/@href')[0]
req = self.make_requests_from_url(response.urljoin(href))
req.callback = self.parse_shangdong_xml
yield req
def parse(self, response):
a = response.xpath('//div[@class="W750 Right"]//li//a')
for a1 in a:
item = BiddinginfospiderItem()
href = response.urljoin(a1.xpath('.//@href').extract_first())
title = a1.xpath(".//text()").extract_first().strip()
ctime = a1.xpath('..//..//span//text()').extract_first()
city = '南方电网'
item.update(
href=href,
title=title,
ctime=ctime,
city=city
)
yield item
def parse_page(self, response):
rs = json.loads(response.body.decode('utf8'))
rs = rs['data'].get("datalist", False)
for a in rs:
item = BiddinginfospiderItem()
item[
'href'] = 'http://www.wysggzy.cn:81/hyweb/wysebid/bidDetails.do?handle=1&tenderProjCode={0}¬iceType=1&flag=1&tenderProjId={1}&proj_id={2}&pre_evaId=&evaId={3}&signUpType={4}'.format(
a['tenderProjCode'], a['tenderProjId'], a['proj_id'],
a['evaId'], a['signUpType'])
item['title'] = a['noticeTitle']
item['ctime'] = a['sendTime']
item['city'] = '武夷山'
data = {
"tenderProjCode": a['tenderProjCode'],
"noticeType": "1",
"noticeId": ""
}
# yield scrapy.Request(url='http://www.wysggzy.cn:81/hyweb/transInfo/getProjBuildNoticeById.do',
# dont_filter=True, callback=self.parse_item, method="POST", body=json.dumps(data),
# meta={'meta': item, })
yield item
def parse_start_url(self, response):
print('request_url= ', response.request.url)
li = response.xpath('//li[@class="now-hd-items clearfix"]')
for l in li:
item = BiddinginfospiderItem()
a = l.xpath('./a')
title = a.xpath('.//@title').extract_first()
href = response.urljoin(a.xpath('.//@href').extract_first())
ctime = self.get_ctime(l.xpath('.//span//text()'))
item.update(
title=title,
ctime=ctime,
href=href,
)
# yield scrapy.Request(url=href, dont_filter=True, callback=self.parse_item, meta={'item': item})
yield item
def parse_start_url(self, response):
print('request_url= ', response.request.url)
li = response.xpath('//div[@class="list_service"]//tr')
for l in li:
item = BiddinginfospiderItem()
a = l.xpath('.//a')
title = a.xpath('.//@title').extract_first()
href = response.urljoin(a.xpath('.//@href').extract_first())
ctime = self.get_ctime(l.xpath(".//td[2]//text()"))
item.update(
category=self.category,
title=title,
ctime=ctime,
href=href,
)
# yield scrapy.Request(url=href, dont_filter=True, callback=self.parse_item, meta={'item': item})
yield item
def parse_start_url(self, response):
print('request_url= ', response.request.url)
li = response.xpath('//li[@name="li_name"]//a')
for a in li:
item = BiddinginfospiderItem()
title = a.xpath('@title').get()
href = response.urljoin(a.xpath('.//@href').get())
ctime = self.get_ctime(a.xpath('.//em[1]//text()'))
item.update(
ctime=ctime,
industry=self.industry,
category=self.category,
title=title,
href=href,
)
# print(item)
yield item
def parse_start_url(self, response):
print('request_url= ', response.request.url)
li = response.xpath('//ul[@class="ewb-news-items"]//li')
for l in li:
item = BiddinginfospiderItem()
a = l.xpath('.//a')
title = a.xpath('.//@title').extract_first()
href = response.urljoin(a.xpath('.//@href').extract_first())
ctime = self.get_ctime(a.xpath('.//span//text()'))
item.update(
city="湖北",
title=title,
ctime=ctime,
href=href,
)
yield item
def parse_start_url(self, response):
print('request_url= ', response.request.url)
li = response.xpath('//li[@class="list-item"]')
for l in li:
item = BiddinginfospiderItem()
a = l.xpath('./a')
title = a.xpath('.//@title').extract_first()
href = response.urljoin(a.xpath('.//@href').extract_first())
ctime = self.get_ctime(a.xpath('.//span//text()'))
item.update(
industry=self.industry,
category=self.category,
title=title,
ctime=ctime,
href=href,
)
yield item
def parse_start_url(self, response):
a_list = response.xpath('//div[@id="listChangeDiv"]//td//a')
for a in a_list:
item = BiddinginfospiderItem()
item['href'] = response.urljoin(a.xpath('@href').get())
item['ctime'] = a.xpath('../../td[3]//text()').get()
item['title'] = a.xpath("@title").get()
# print(item)
yield item
def parse_start_url(self, response):
li = response.xpath('//div[@class="lb-link"]/ul//li')
for l in li:
item = BiddinginfospiderItem()
a = l.xpath('.//a')
title = a.xpath("@title").get()
href = a.xpath("@href").get()
ctime = self.get_ctime(l.xpath('.//span[@class="bidDate"]//text()'))
item.update(
industry=self.industry,
category=self.category,
title=title,
ctime=ctime,
href=href,
)
# print(item)
yield item
def parse_page(self, response):
print(response.request.url)
a_lst = response.xpath('//table[@class="wsbs-table"]//a')
for a in a_lst:
item = BiddinginfospiderItem()
title = a.xpath('.//text()').extract_first()
href = response.urljoin(a.xpath('.//@href').extract_first())
ctime = self.get_ctime(a.xpath('../../td//text()'))
item.update(
category=self.category,
industry=self.industry,
title=title,
ctime=ctime,
href=href,
city="广东",
)
yield item
def parse(self, response):
# a标签
a = response.xpath('//ul[@class="newslist"]//li//a')
for a1 in a:
item = BiddinginfospiderItem()
item['href'] = response.urljoin(a1.xpath('.//@href').get())
item['title'] = a1.xpath(".//h1//text()").getall()[3].strip()
item['ctime'] = a1.xpath('normalize-space(string(.//div[@class="newsDate"]))').get().replace('/','-').replace(' ','-')
yield item
def parse_start_url(self, response):
print('reponse_request_url= ', response.request.url)
li = response.xpath('//div[@id="listChangeDiv"]//li')
for line in li:
item = BiddinginfospiderItem()
a = line.xpath('.//a')
item['href'] = response.urljoin(a.xpath('@href').get())
item['title'] = a.xpath('@title').get()
item['ctime'] = line.xpath(".//span/text()").get()
yield item
def parse_page(self, response):
res = Selector(response)
li_lst = res.xpath('//tr[@class="gridview1_RowStyle"]')
for l in li_lst:
item = BiddinginfospiderItem()
a = l.xpath(".//a")
title = a.xpath('.//text()').extract_first()
href = response.urljoin(a.xpath('.//@href').extract_first())
c = l.xpath('.//td[@class="gridview_RowTD"][last()]')
ctime = self.get_ctime(c)
item.update(
category=self.category,
industry=self.industry,
title=title,
ctime=ctime,
href=href,
)
# yield scrapy.Request(url=href, dont_filter=True, callback=self.parse_item, meta={'item': item})
yield item
def parse(self, response):
# a标签
a = response.xpath('//div[@class="lb-link"]//ul//li//a')
for a1 in a:
item = BiddinginfospiderItem()
item['href'] = response.urljoin(a1.xpath('.//@href').get())
item['title'] = a1.xpath(".//@title").get().strip()
item['ctime'] = a1.xpath('.//span[3]//text()').get()
yield item
def parse(self, response):
rs = json.loads(response.body.decode('utf8'))
for a1 in rs:
item = BiddinginfospiderItem()
item['href'] = a1['pdf_url']
item['title'] = a1['message_title']
time0 = time.localtime(int(str(a1['publish_time'])[0:10]))
item['ctime'] = time.strftime("%Y-%m-%d", time0)
yield item
def parse_start_url(self, response):
res = Selector(text=response.text[11:-2])
a_list = res.xpath('//a')
for a in a_list:
item = BiddinginfospiderItem()
item['href'] = urljoin("http://qdstc.qingdao.gov.cn",
a.xpath('@href').get())
item['ctime'] = a.xpath('../../td[3]//text()').get()
item['title'] = a.xpath("@title").get()
# print(item)
yield item
def parse_start_url(self, response):
print('request_url= ', response.request.url)
li = json.loads(str(response.body, "utf-8"))
data = li.get("rows")
article_tmp_url = "http://epp.ctg.com.cn/infoview/?fileId={0}&openFor=ZBGG&typeFor=undefined"
for li in data:
item = BiddinginfospiderItem()
title = li.get('TITLE')
ctime = li.get('CREATED_TIME')
id = li.get('ARTICLE_ID')
href = article_tmp_url.format(id)
item.update(
industry=self.industry,
category=self.category,
title=title,
ctime=ctime,
href=href,
)
# print(item)
yield item
def parse_page(self, response):
li_lst = response.xpath(
'//div[@class="abstract-box mg-t25 ebnew-border-bottom mg-r15"]')
for l in li_lst:
item = BiddinginfospiderItem()
a = l.xpath('.//a')
title = a.xpath('.//@title').extract_first()
href = response.urljoin(a.xpath('.//@href').extract_first())
ctime = self.get_ctime(l.xpath('.//i[2]//text()'))
city = l.xpath(
'.//div[@class="abstract-content-items fl pd-l15 pd-t20 pd-b20 width-50"][2]//p[2]//span[2]//text()'
).extract_first()
item.update(
title=title,
ctime=ctime,
href=href,
city=city,
)
yield item
def parse_page(self, response):
res = scrapy.Selector(response)
article_tmp_url = 'http://ec.ccccltd.cn/PMS/gysCggg.shtml?id={0}'
li = res.xpath('//td[@class="listCss"]//a')
for a in li:
item = BiddinginfospiderItem()
title = a.xpath('normalize-space(string(.))').get()
x = "".join(
a.xpath('.//@href').get().replace("\\r", "").replace(
"\\n", "").split())[23:-3]
href = article_tmp_url.format(x)
ctime = self.get_ctime(
a.xpath('../following-sibling::td[1]//text()'))
item.update(
title=title,
href=href,
ctime=ctime,
)
# print(item)
yield item
def parse(self, response):
rs = json.loads(response.body.decode('utf8'))
rs = rs['_rows']
for a1 in rs:
item = BiddinginfospiderItem()
item[
'href'] = 'http://ecm.crcc.cn/unlogin/queryPurchaseTenderDetailInit.jhtml?model=1&id=' + a1[
'id']
item['title'] = a1['v_notice_title']
item['ctime'] = a1['d_createdate']
yield item
def parse(self, response):
rs = json.loads(response.body.decode('utf8'))
rs = rs['_rows']
for a1 in rs:
item = BiddinginfospiderItem()
item[
'href'] = 'http://ece.crcc.cn/homepage/inviteInfo.jhtml?type=1&id=' + str(
a1['inviteid'])
item['title'] = a1['texttitle']
item['ctime'] = a1['recordtime'][0:10]
yield item
def parse_start_url(self, response):
print('request_url= ', response.request.url)
li = response.xpath('//table[@class="table_text"]//tr')
for l in li[1:]:
item = BiddinginfospiderItem()
a = l.xpath('.//a')
title = a.xpath('.//@title').extract_first()
href = response.urljoin(a.xpath('.//@href').extract_first())
ctime = self.get_ctime(a.xpath('.//td[5]//span//text()'))
industry = l.xpath(".//td[2]//span//text()").extract_first()
city = l.xpath(".//td[3]//span//@title").extract_first()
item.update(
industry=industry,
title=title,
ctime=ctime,
href=href,
city=city,
)
# yield scrapy.Request(url=href, dont_filter=True, callback=self.parse_item, meta={'item': item})
yield item
def parse(self, response):
rs = json.loads(response.body.decode('utf8'))
rs = eval(rs['return'])['Table']
for a in rs:
item = BiddinginfospiderItem()
item['href'] = response.urljoin(a['href'])
item['title'] = a['title']
item['ctime'] = a['infodate']
item['city'] = a['infoc']
# yield scrapy.Request(url=item['href'], dont_filter=True, callback=self.parse_item, meta={'meta': item, })
yield item
