def content_parse(self, response):
pipleitem = DongnanfumianItem()
pipleitem['S6'] = response.meta['date']
pipleitem['S0'] = response.meta['id']
pipleitem['S1'] = response.url
pipleitem['S4'] = response.meta['title']
pipleitem['S3a'] = '文章'
pipleitem['G1'] = response.meta['author']
pipleitem['S3d'] = response.xpath('string(//div[@class="fl m-home_href"])').extract_first()
pipleitem['S7'] = "PC"
pipleitem['S2'] = '维科号'
pipleitem['Q1'] = response.xpath('string(//div[@class="main"])').extract_first()
pipleitem['S5'] = helper.get_localtimestamp()
return pipleitem
def content_parse(self, response):
pipleitem = DongnanfumianItem()
pipleitem['S6'] = response.meta['date']
pipleitem['S0'] = response.meta['id']
pipleitem['S1'] = response.url
pipleitem['S4'] = response.meta['title']
pipleitem['S3a'] = '文章'
pipleitem['G1'] = response.meta['author']
pipleitem['S3d'] = None
pipleitem['S7'] = "APP"
pipleitem['S2'] = '懂车帝APP'
pipleitem['Q1'] = None
pipleitem['S5'] = helper.get_localtimestamp()
return pipleitem
def content_parse(self, response):
pipleitem = DongnanfumianItem()
pipleitem['S6'] = response.meta['date']
pipleitem['S0'] = response.meta['id']
pipleitem['S1'] = response.url
pipleitem['S4'] = response.meta['title']
pipleitem['S3a'] = '文章'
pipleitem['G1'] = response.meta['author']
pipleitem['S3d'] = None
pipleitem['S7'] = "APP"
pipleitem['S2'] = '时代财经APP'
pipleitem['Q1'] = re.findall('content:([\S\s]*?)groupId:', response.text)[0]
pipleitem['S5'] = helper.get_localtimestamp()
return pipleitem
def content_parse(self, response):
pipleitem = DongnanfumianItem()
pipleitem['S6'] = response.meta['date']
pipleitem['S0'] = response.meta['id']
pipleitem['S1'] = response.url
pipleitem['S4'] = response.meta['title']
pipleitem['S3a'] = '文章'
pipleitem['G1'] = response.meta['author']
pipleitem['S3d'] = None
pipleitem['S7'] = "APP"
pipleitem['S2'] = '腾讯新闻app'
# pipleitem['Q1'] = response.xpath('string(//div[@class="_1Xa3FHZJUzr6lzb4nMjOa4"])').extract_first()
pipleitem['Q1'] = response.meta['content']
pipleitem['S5'] = helper.get_localtimestamp()
return pipleitem
def content_parse(self, response):
pipleitem = DongnanfumianItem()
pipleitem['S6'] = response.meta['date']
pipleitem['S0'] = response.meta['id']
pipleitem['S1'] = response.url
pipleitem['S4'] = response.meta['title']
pipleitem['S3a'] = '文章'
pipleitem['G1'] = response.meta['author']
pipleitem['S3d'] = None
pipleitem['S7'] = "APP"
pipleitem['S2'] = '天天快报'
pipleitem['Q1'] = response.xpath(
'string(//div[@class="content-box"])').extract()
pipleitem['S5'] = helper.get_localtimestamp()
return pipleitem
def content_parse(self, response):
pipleitem = DongnanfumianItem()
pipleitem['S6'] = response.meta['date']
pipleitem['S0'] = response.meta['id']
pipleitem['S1'] = response.url
pipleitem['S4'] = response.meta['title']
pipleitem['S3a'] = '文章'
pipleitem['G1'] = response.meta['author']
pipleitem['S3d'] = None
pipleitem['S7'] = "PC"
pipleitem['S2'] = '老司机'
content = response.xpath(
'string(//div[@class="threa-main-box"])').extract_first()
if len(content) != 0: content = content.replace('\t', '')
pipleitem['Q1'] = content
pipleitem['S5'] = helper.get_localtimestamp()
return pipleitem
def content_parse(self, response):
pipleitem = DongnanfumianItem()
pipleitem['S6'] = response.css('.xd-b-b p span::text').extract_first()
pipleitem['S0'] = re.findall('/(\d{5,})', response.url)[0]
pipleitem['S1'] = response.url
pipleitem['S4'] = response.css('head title::text').extract_first()
pipleitem['S3a'] = '文章'
author = re.findall(
'(.*?)\d{4}',
response.xpath(
'string(//div[@class="xd-b-b"]/p)').extract_first())[0]
pipleitem['G1'] = author
pipleitem['S3d'] = None
pipleitem['S7'] = "PC"
pipleitem['S2'] = '经济观察网'
pipleitem['Q1'] = response.xpath(
'string(//div[@class="xx_boxsing"])').extract_first()
pipleitem['S5'] = helper.get_localtimestamp()
return pipleitem