def parse_content(self, response):
item = GovCnItem()
item['datePublished'] = response.meta.get('time').strip()
item['headline'] = response.meta.get('title')
item['Bigtype'] = response.meta.get('Bigtype')
item['articleBody'] = response.css('td.b12c').xpath(
'string(.)').extract_first()
item['annex'] = [
urlparse.urljoin(response.url, each_pic)
for each_pic in response.css('td.b12c img::attr(src)').extract()
]
if not item['articleBody']:
item['articleBody'] = response.css('div#UCAP-CONTENT').xpath(
'string(.)').extract_first()
item['annex'] = [
urlparse.urljoin(response.url, each_pic) for each_pic in
response.css('div#UCAP-CONTENT img::attr(src)').extract()
]
try:
item['copyrightHolder'] = response.css(
'span.font::text').extract_first().split(u'：')[1].strip()
except:
item['copyrightHolder'] = ''
item['url'] = response.url
yield item
def parse_content(self, response):
item = GovCnItem()
item['datePublished'] = ''
item['headline'] = response.meta.get('title')
item['Bigtype'] = response.meta.get('Bigtype')
item['articleBody'] = response.css('div#UCAP-CONTENT').xpath(
'string(.)').extract_first()
item['annex'] = [
urlparse.urljoin(response.url, each_pic) for each_pic in
response.css('div#UCAP-CONTENT img::attr(src)').extract()
]
item['copyrightHolder'] = ''
item['url'] = response.url
yield item