def parse_one(self, response):
item = ShanghaioneItem()
item['title'] = re.findall(r'<h1>.*?</h1>',
response.body)[0].decode("gbk")[4:-5]
title_link = re.findall(r'<h1>.*?</h1>',
response.body)[0].decode("gbk")[4:-5]
m2 = hashlib.md5()
m2.update(title_link.encode("utf-8"))
item['md5'] = m2.hexdigest()
times = re.findall(r"t =\'.*\'", response.body)[0][4:-1]
try:
time.strptime(times, "%Y-%m-%d")
item['times'] = times
except:
item['times'] = ""
#item['content'] = response.xpath("//div[@id='zoom']/div").extract()[0]
if response.xpath("//div[@id='zoom']/div"):
item['content'] = response.xpath(
"//div[@id='zoom']/div").extract()[0]
else:
item['content'] = ""
item['yuan'] = "广东省经济和信息化委员会"
item["province"] = "广东"
# print item
yield item
def parse_one(self, response):
item = ShanghaioneItem()
item['title'] = response.xpath("//div[@class='nstit']/h1/text()").extract()[0]
title_link = response.xpath("//div[@class='nstit']/h1/text()").extract()[0]
m2 = hashlib.md5()
m2.update(title_link.encode("utf-8"))
item['md5'] = m2.hexdigest()
times = response.xpath("//div[@class='nstimes0']/text()").extract()[0].strip().split()[2][3:]
try:
time.strptime(times, "%Y-%m-%d")
item['times'] = times
except:
item['times'] = ""
item['content'] = response.xpath("//div[@class='TRS_Editor']").extract()[0]
item['yuan'] = "江苏省经济和信息化委员会"
item["province"] = "江苏"
yield item
def parse_one(self, response):
item = ShanghaioneItem()
item['title'] = response.xpath("//td[@class='title']/text()").extract()[0]
title_link = response.xpath("//td[@class='title']/text()").extract()[0]
m2 = hashlib.md5()
m2.update(title_link.encode("utf-8"))
item['md5'] = m2.hexdigest()
times = response.xpath("//td[@style='line-height:20px;font-size:12px;']/text()").extract()[-1].replace("印发时间：","")
try:
time.strptime(times, "%Y-%m-%d")
item['times'] = times
except:
item['times'] = ""
item['content'] = response.xpath("//div[@id='zoom']").extract()
item['yuan'] = "浙江省经济和信息化委员会"
item["province"] = "浙江"
yield item
def parse_one(self, response):
item = ShanghaioneItem()
item['title'] = response.xpath("//h1[@id='ivs_title']/text()").extract()[0]
title_link = response.xpath("//h1[@id='ivs_title']/text()").extract()[0]
m2 = hashlib.md5()
m2.update(title_link.encode("utf-8"))
item['md5'] = m2.hexdigest()
a = response.xpath("//h3[@class='view_tit_1']/text()").extract()[0]
times = re.findall(r"\d.*\d", a)[0]
try:
time.strptime(times, "%Y-%m-%d")
item['times'] = times
except:
item['times'] = ""
item['content'] = response.xpath("//div[@id='ivs_content']").extract()[0]
item['yuan'] = "上海市经济和信息化委员会"
item["province"] = "上海"
yield item