def _parse_research(self, response):
reports = response.xpath(".//*[@id='ulNewsList']//li")
if len(reports)>0:
for report in reports:
item = IndustryReportSpiderItem()
item["industry_large_category"] = response.meta["large_category"]
item["industry_mid_category"] = response.meta["mid_category"]
item["report_name"] = clean_text(report.xpath(".//dt//text()").extract()[0].strip())
industry_small_chs_name = parseIndustryName(item["report_name"])
if industry_small_chs_name != None:
item["industry_small_chs_name"] = industry_small_chs_name
page_url = report.xpath(".//@href").extract()[0]
item["report_link"] = page_url
report_time = clean_text(report.xpath(".//*[@class='time']").extract()[0].strip())
if len(report_time) >0:
item["report_revision_time"] = report_time.split(u"：")[1]
date, date_precision = parse_date(item["report_revision_time"])
try:
item["report_revision_time_standard"] = date.replace(tzinfo=pytz.timezone('Asia/Shanghai'))
except:
pass
item["source_domain"] = self.allowed_domains[0]
item["source_name"] = u"中国产业洞察网"
item["price_free"] = False
yield item
def _parse_free(self, response):
reports = response.xpath(".//*[@class='tul3']//li")
if len(reports)>0:
for report in reports:
item = IndustryReportSpiderItem()
item["industry_large_category"] = response.meta["large_category"]
item["report_name"] = clean_text(report.xpath(".//a//text()").extract()[0].strip())
industry_small_chs_name = parseIndustryName(item["report_name"])
if industry_small_chs_name != None:
item["industry_small_chs_name"] = industry_small_chs_name
page_url = report.xpath(".//@href").extract()[0]
item["report_link"] = page_url
report_content = self.parseTimeContent(page_url)
if report_content != None:
item["report_content"] = report_content
report_time = clean_text(report.xpath(".//span//text()").extract()[0].strip())
if (len(report_time) > 0):
item["report_revision_time"] = report_time
date, date_precision = parse_date(item["report_revision_time"])
try:
item["report_revision_time_standard"] = date.replace(tzinfo=pytz.timezone('Asia/Shanghai'))
except:
pass
item["source_domain"] = self.allowed_domains[0]
item["source_name"] = u"中国产业洞察网"
item["price_free"] = True
yield item
def parse_item(self, response):
item = IndustryReportSpiderItem()
item['report_link'] = response.url
item['source_name'] = u"艾瑞网"
item['source_domain'] = self.allowed_domains[0]
item['report_name'] = clean_text(response.xpath("//*[@class='content_title']/text()").extract()[0].strip())
price = response.xpath(u"//*[contains(text(), '价格')]/text()").extract()[0]
item['price_free'] = True if u"免费" in price else False
infodatas = response.xpath("//*[@class='content_titleinfoa']/span//text()").extract()
for text in infodatas:
try:
if u"页数" in text:item['report_page_count'] = re.findall(ur'([0-9]+)', text)[0]
except:pass
try:
if u"图表" in text:item['report_graph_count'] = re.findall(ur'([0-9]+)', text)[0]
except:pass
try:
if u"-" in text:
item['report_revision_time'] = text
item['report_revision_time_standard'] = parse_date(item['report_revision_time'])
except:pass
item['industry_large_category'] =u"信息传输、软件和信息技术服务业"
try:
item['industry_mid_category'] = clean_text(response.xpath("//*[@class='content_titleinfoa']//a/text()").extract()[0].strip())
except:
pass
# if item['price_free']:
# self.browser.get(response.url)
# self.browser.find_element_by_xpath("//*[@class='download']/a").click()
# WebDriverWait(self.browser, 20).until(EC.presence_of_element_located((By.XPATH, ".//*[@id='ButtonBox']/input")))
# Confirm = self.browser.find_element_by_xpath(".//*[@id='ButtonBox']/input")
# Confirm.click()
# WebDriverWait(self.browser, 20).until(EC.staleness_of(Confirm))
# if ".pdf" in self.browser.current_url:item['pdf_Link'] = self.browser.current_url
return item
def _parse_hg(self, response):
reports = response.xpath(".//*[@class='yahei f14']")
if len(reports) > 0:
for report in reports:
item = IndustryReportSpiderItem()
item["industry_large_category"] = response.meta[
"large_category"]
item["report_name"] = clean_text(
report.xpath(".//a/text()").extract()[0].strip())
page_url = report.xpath(".//a//@href").extract()[0]
item["report_link"] = page_url
report_time = clean_text(
report.xpath(".//*[@name='deliveddate']/text()").extract()
[0].strip())
if report_time != None:
item["report_revision_time"] = report_time
item["source_domain"] = self.allowed_domains[0]
item["source_name"] = u"国研网"
date, date_precision = parse_date(item["report_revision_time"])
item["report_revision_time_standard"] = date.replace(
tzinfo=pytz.timezone('Asia/Shanghai'))
dict = self.parseContent(page_url)
if dict["free"] == False:
item["price_free"] = False
else:
item["price_free"] = True
if (dict["url"][0] == "pdf"):
item["pdf_Link"] = dict["url"][1]
else:
item["content_Link"] = dict["url"][1]
yield item
def _parse_research(self, response):
reports = response.xpath(".//*[@id='ulNewsList']//li")
if len(reports) > 0:
for report in reports:
item = IndustryReportSpiderItem()
item["industry_large_category"] = response.meta[
"large_category"]
item["industry_mid_category"] = response.meta["mid_category"]
item["report_name"] = clean_text(
report.xpath(".//dt//text()").extract()[0].strip())
industry_small_chs_name = parseIndustryName(
item["report_name"])
if industry_small_chs_name != None:
item["industry_small_chs_name"] = industry_small_chs_name
page_url = report.xpath(".//@href").extract()[0]
item["report_link"] = page_url
report_time = clean_text(
report.xpath(".//*[@class='time']").extract()[0].strip())
if len(report_time) > 0:
item["report_revision_time"] = report_time.split(u"：")[1]
date, date_precision = parse_date(
item["report_revision_time"])
try:
item["report_revision_time_standard"] = date.replace(
tzinfo=pytz.timezone('Asia/Shanghai'))
except:
pass
item["source_domain"] = self.allowed_domains[0]
item["source_name"] = u"中国产业洞察网"
item["price_free"] = False
yield item
def _parse_free(self, response):
reports = response.xpath(".//*[@class='tul3']//li")
if len(reports) > 0:
for report in reports:
item = IndustryReportSpiderItem()
item["industry_large_category"] = response.meta[
"large_category"]
item["report_name"] = clean_text(
report.xpath(".//a//text()").extract()[0].strip())
industry_small_chs_name = parseIndustryName(
item["report_name"])
if industry_small_chs_name != None:
item["industry_small_chs_name"] = industry_small_chs_name
page_url = report.xpath(".//@href").extract()[0]
item["report_link"] = page_url
report_content = self.parseTimeContent(page_url)
if report_content != None:
item["report_content"] = report_content
report_time = clean_text(
report.xpath(".//span//text()").extract()[0].strip())
if (len(report_time) > 0):
item["report_revision_time"] = report_time
date, date_precision = parse_date(
item["report_revision_time"])
try:
item["report_revision_time_standard"] = date.replace(
tzinfo=pytz.timezone('Asia/Shanghai'))
except:
pass
item["source_domain"] = self.allowed_domains[0]
item["source_name"] = u"中国产业洞察网"
item["price_free"] = True
yield item
def _parse_item(self, response):
reports = response.xpath(".//*[@class='info']")
if len(reports) > 0:
for report in reports:
item = IndustryReportSpiderItem()
item["industry_large_category"] = response.meta[
"large_category"]
item["industry_mid_category"] = response.meta["mid_category"]
item["report_name"] = clean_text(
report.xpath(".//h3//a/text()").extract()[0].strip())
industry_small_chs_name = parseIndustryName(
item["report_name"])
if industry_small_chs_name != None:
item["industry_small_chs_name"] = industry_small_chs_name
page_url = report.xpath(".//@href").extract()[0]
url = urljoin(self.base_url, page_url)
item["report_link"] = url
string = clean_text(
report.xpath(" //*[@class='rdate']//span/text()").extract(
)[0].strip())
temp = self.parseItem(string)
if len(temp) == 1:
item["report_revision_time"] = temp[0][0]
item["report_page_count"] = temp[0][1]
item["report_graph_count"] = temp[0][2]
date, date_precision = parse_date(
item["report_revision_time"])
item["report_revision_time_standard"] = date.replace(
tzinfo=pytz.timezone('Asia/Shanghai'))
item["source_domain"] = self.allowed_domains[0]
item["source_name"] = u"中国投资咨询网"
item["price_free"] = False
yield item
if_nextpage = response.xpath(".//*[@class='zw']")
if len(if_nextpage) > 0:
if (if_nextpage.xpath(".//text()").extract()[-1]
) == u'下一页': #存在翻页
page_url = if_nextpage.xpath(".//@href").extract()[-1]
url = urljoin(self.base_url, page_url)
request = FormRequest(url,
callback=self._parse_item,
dont_filter=True)
request.meta["large_category"] = response.meta[
"large_category"]
request.meta["mid_category"] = response.meta[
"mid_category"]
yield request
def _parse_item(self, response):
reports = response.xpath(".//*[@class='img_des']/a")
if len(reports) > 0:
for report in reports:
item = IndustryReportSpiderItem()
item["industry_large_category"] = response.meta[
"large_category"]
item["industry_mid_category"] = response.meta["mid_category"]
item["report_name"] = clean_text(
report.xpath("./text()").extract()[0].strip())
industry_small_chs_name = parseIndustryName(
item["report_name"])
if industry_small_chs_name != None:
item["industry_small_chs_name"] = industry_small_chs_name
page_url = report.xpath(".//@href").extract()[0]
url = urljoin(self.base_url, page_url)
item["report_link"] = url
report_time = self.parseTime(item["report_link"])
if report_time != None:
item["report_revision_time"] = report_time
item["source_domain"] = self.allowed_domains[0]
item["source_name"] = u"欧咨网"
date, date_precision = parse_date(item["report_revision_time"])
item["report_revision_time_standard"] = date.replace(
tzinfo=pytz.timezone('Asia/Shanghai'))
item["price_free"] = False
yield item
if len(response.xpath(".//*[@class='page']//@href")) > 1: #存在翻页
page_len = clean_text(
response.xpath(
".//*[@class='page']//*[@class='fl_l']/text()").
extract()[0].strip())
nextPageurl = response.xpath(
".//*[@class='page']//@href").extract()[-1]
finds = self.pattern_page.findall(page_len)
currentPage = finds[0][0]
totlePage = finds[0][1]
if currentPage != totlePage:
url = urljoin(self.base_url, nextPageurl)
request = FormRequest(url,
callback=self._parse_item,
dont_filter=True)
request.meta["large_category"] = response.meta[
"large_category"]
request.meta["mid_category"] = response.meta[
"mid_category"]
yield request
def report_para(self, item, report):
revision_time = clean_text(report.xpath("..//*[@class='sp1']/text()").extract()[0].split(u"：")[1].strip())
if self.pattern.match(revision_time):
item["report_revision_time"] = revision_time
else:
textlst = report.xpath("../*[@class='main']/text()").extract()[0].replace(u"】 ", u"【").split(u"【")
for text in range(len(textlst)+1):
if textlst[text].endswith(u"日期"):
item["report_revision_time"] = clean_text(textlst[text+1].strip())
break
try:
date, date_precision = parse_date(item["report_revision_time"])
dateTimezone = date.replace(tzinfo=pytz.timezone('Asia/Shanghai'))
item["report_revision_time_standard"] = dateTimezone
except:
pass
def _parse_item(self, response):
reports = response.xpath(".//*[@class='info']")
if len(reports)>0:
for report in reports:
item = IndustryReportSpiderItem()
item["industry_large_category"] = response.meta["large_category"]
item["industry_mid_category"] = response.meta["mid_category"]
item["report_name"] = clean_text(report.xpath(".//h3//a/text()").extract()[0].strip())
industry_small_chs_name = parseIndustryName(item["report_name"])
if industry_small_chs_name != None:
item["industry_small_chs_name"] = industry_small_chs_name
page_url = report.xpath(".//@href").extract()[0]
url = urljoin(self.base_url, page_url)
item["report_link"] = url
string =clean_text(report.xpath(" //*[@class='rdate']//span/text()").extract()[0].strip())
temp = self.parseItem(string)
if len(temp)==1:
item["report_revision_time"] = temp[0][0]
item["report_page_count"] = temp[0][1]
item["report_graph_count"] = temp[0][2]
date, date_precision = parse_date(item["report_revision_time"])
item["report_revision_time_standard"] = date.replace(tzinfo=pytz.timezone('Asia/Shanghai'))
item["source_domain"] = self.allowed_domains[0]
item["source_name"] = u"中国投资咨询网"
item["price_free"] = False
yield item
if_nextpage = response.xpath(".//*[@class='zw']")
if len(if_nextpage)>0:
if (if_nextpage.xpath(".//text()").extract()[-1])==u'下一页': #存在翻页
page_url =if_nextpage.xpath(".//@href").extract()[-1]
url = urljoin(self.base_url, page_url)
request = FormRequest(url, callback=self._parse_item, dont_filter=True)
request.meta["large_category"] = response.meta["large_category"]
request.meta["mid_category"] = response.meta["mid_category"]
yield request
def _parse_item(self, response):
reports = response.xpath(".//*[@class='clistdl']")
for report in reports:
item = IndustryReportSpiderItem()
item["industry_large_category"] = response.meta["large_category"]
item["industry_mid_category"] = response.meta["mid_category"]
item["report_name"] = clean_text(report.xpath(".//dt/a/text()").extract()[0].strip())
if len(report.xpath(".//dd//*[@class='cxgrep']//@title"))>0:
industry = clean_text(report.xpath(".//dd//*[@class='cxgrep']//@title").extract()[0].strip())
else:
industry = item["report_name"]
industry_small_chs_name = parseIndustryName(industry)
if industry_small_chs_name != None:
item["industry_small_chs_name"] = industry_small_chs_name
page_url = report.xpath(".//@href").extract()[0]
item["report_link"] = page_url
item["report_revision_time"] = clean_text(report.xpath(".//dt/span/text()").extract()[0].strip())
item["source_domain"] = self.allowed_domains[0]
item["source_name"] = u"中国报告大厅"
date, date_precision = parse_date(item["report_revision_time"])
item["report_revision_time_standard"] = date.replace(tzinfo=pytz.timezone('Asia/Shanghai'))
item["price_free"] = False
yield item
def _parse_item(self, response):
reports = response.xpath(".//*[@class='img_des']/a")
if len(reports)>0:
for report in reports:
item = IndustryReportSpiderItem()
item["industry_large_category"] = response.meta["large_category"]
item["industry_mid_category"] = response.meta["mid_category"]
item["report_name"] = clean_text(report.xpath("./text()").extract()[0].strip())
industry_small_chs_name = parseIndustryName(item["report_name"])
if industry_small_chs_name != None:
item["industry_small_chs_name"] = industry_small_chs_name
page_url = report.xpath(".//@href").extract()[0]
url = urljoin(self.base_url, page_url)
item["report_link"] = url
report_time = self.parseTime(item["report_link"])
if report_time != None:
item["report_revision_time"] = report_time
item["source_domain"] = self.allowed_domains[0]
item["source_name"] = u"欧咨网"
date, date_precision = parse_date(item["report_revision_time"])
item["report_revision_time_standard"] = date.replace(tzinfo=pytz.timezone('Asia/Shanghai'))
item["price_free"] = False
yield item
if len(response.xpath(".//*[@class='page']//@href"))>1: #存在翻页
page_len = clean_text(response.xpath(".//*[@class='page']//*[@class='fl_l']/text()").extract()[0].strip())
nextPageurl = response.xpath(".//*[@class='page']//@href").extract()[-1]
finds = self.pattern_page.findall(page_len)
currentPage = finds[0][0]
totlePage = finds[0][1]
if currentPage != totlePage:
url = urljoin(self.base_url, nextPageurl)
request = FormRequest(url, callback=self._parse_item, dont_filter=True)
request.meta["large_category"] = response.meta["large_category"]
request.meta["mid_category"] = response.meta["mid_category"]
yield request
