def parse_item(self, response):
loader = ChinaLoader(item=NewsItem(), response=response)
loader.add_xpath('title', '//h1[@id="chan_newsTitle"]/text()')
loader.add_value('url', response.url)
loader.add_xpath('text', '//div[@id="chan_newsDetail"]//text()')
loader.add_xpath('datetime', '//div[@id="chan_newsInfo"]/text()', re='(\d+-\d+-\d+\s\d+:\d+:\d+)')
loader.add_xpath('source', '//div[@id="chan_newsInfo"]/text()', re='来源：(.*)')
loader.add_value('website', '中华网')
yield loader.load_item()
def parse_item2(self, response):
item = NewsItem()
item['title'] = response.xpath(
'//title/text()').extract_first().strip()
item['url'] = response.url
item['text'] = ''.join(
response.xpath(
'//div[@id="chan_newsDetail"]//p/text()').extract()).strip()
item['datetime'] = response.xpath(
'//div[@id="chan_newsInfo"]/text()').re_first(
'(\d+-\d+-\d+\s\d+:\d+:\d+)')
item['source'] = response.xpath(
'//div[@id="chan_newsInfo"]/text()').re_first('(;.*?;)')
item['website'] = '中华网'
yield item
def parse_item(self, response):
loader = ChinaLoader(item=NewsItem(), response=response)
loader.add_xpath('title', "h1[@id='chan_newsTitle']/text()")
loader.add_value('url', response.url)
loader.add_xpath('text', "//div[@id='chan_newsDetail']//text()")
loader.add_xpath(
"datetime",
"//div[@class='chan_newsInfo_source']/span[@class='time']/text()",
re='(\d+-\d+-\d+\s\d+:\d+:\d+)')
loader.add_xpath(
"source",
"//div[@class='chan_newsInfo_source']/span[@class='source']/text()"
)
loader.add_value('website', '中华网')
yield loader.load_item()
def parse_item(self, response):
loader = ChinaLoader(item=NewsItem(), response=response)
#item['domain_id'] = response.xpath('//input[@id="sid"]/@value').get()
#item['name'] = response.xpath('//div[@id="name"]').get()
#item['description'] = response.xpath('//div[@id="description"]').get()
loader.add_xpath('title', '//h1[@id="chan_newsTitle"]/text()')
loader.add_value('url', response.url)
loader.add_xpath('text', '//div[@id="chan_newsDetail"]//text()')
loader.add_xpath('datetime',
'//div[@id="chan_newsInfo"]/text()',
re='(\d+-\d+-\d+\s\d+:\d+:\d+)')
loader.add_xpath('source',
'//div[@id="chan_newsInfo"]/text()',
re='来源：(.*)')
loader.add_value('website', '中华网')
yield loader.load_item()
def parse_item(self, response):
'''
item = NewsItem()
item['title'] = response.xpath('//h1[@id="chan_newsTitle"]/text()').extract_first()
item['url'] = response.url
item['text'] = ''.join(response.xpath('//div[@id="chan_newsDetail"]/text()').extract()).strip()
item['datatime'] = response.xpath('//div[@id="chan_newsInfo"]/text()').re_first('(\d+-\d+-\d+\s\d+:\d+:\d+)')
item['source'] = response.xpath('//div[@id="chan_newsInfo"]/text()').re_first(' 来源:(.*)').strip()
item['website'] = '中华网'
yield item
'''
loader = ChinaLoader(item=NewsItem(), response=response)
loader.add_xpath('title', '//h1[@id="chan_newsTitle"]/text()')
loader.add_xpath('url', response.url)
loader.add_xpath('text', '//div[@id="chan_newsDetail"]/text()')
loader.add_xpath('datetime', '//div[@id="chan_newsInfo"]/text()', re='(\d+-\d+-\d+\s\d+:\d+:\d+)')
loader.add_xpath('source', '//div[@id="chan_newsInfo"]/text()', re=' 来源:(.*)')
loader.add_value('website', '中华网')
yield loader.load_item()
def parse_item(self, response):
# item = NewsItem()
# item['title'] = response.xpath('//*[@id="chan_newsTitle"]/text()').get()
# item['url'] = response.url
# item['source'] = response.xpath('//*[@id="js-article-title"]//span[@class="source"]/text()').get()[3:].strip()
# item['datatime'] = response.xpath('//*[@id="js-article-title"]//span[@class="time"]/text()').get()
# item['text'] = response.xpath('//*[@id="chan_newsDetail"]//p[position() < last()]/text()').getall()
# item['website'] = 'tech.china.com'
# return item
loader = ChinaLoader(item=NewsItem(), response=response)
loader.add_xpath('title', '//*[@id="chan_newsTitle"]/text()')
loader.add_value('url', response.url)
loader.add_xpath(
'text',
'//*[@id="chan_newsDetail"]//p[position() < last()]/text()')
loader.add_xpath(
'datatime',
'//*[@id="js-article-title"]//span[@class="time"]/text()')
loader.add_xpath(
'source',
'//*[@id="js-article-title"]//span[@class="source"]/text()',
re='来源：(.*)')
loader.add_value('website', 'tech.china.com')
# print()
# print(loader.load_item())
# print(type(loader.load_item()))
# print(loader.load_item()['title'])
# print(type(loader.load_item()['title']))
# print(loader.load_item()['url'])
# print(type(loader.load_item()['url']))
# print(loader.load_item()['text'])
# print(type(loader.load_item()['text']))
# print(loader.load_item()['datatime'])
# print(type(loader.load_item()['datatime']))
# print(loader.load_item()['source'])
# print(type(loader.load_item()['source']))
# print()
yield loader.load_item()