def parse(self, response):
links = response.xpath(
"//div[@class='container row main in2']/div/ul/li/a/@href"
).extract()
times = response.xpath(
"//div[@class='container row main in2']/div/ul/li/span/text()"
).extract()
l = len(links)
print_new_number(self.counts, 'HFUT', self.name)
for i in range(l):
report_time = get_localtime(times[i])
if report_time < now_time:
return
report_url = self.domain + links[i][1:]
yield scrapy.Request(report_url,
callback=self.parse_pages,
meta={
'link': report_url,
'number': i + 1
})
number = int(response.url.split('-')[-1].split('.')[0])
last_number = response.xpath(
"//div[@id='pages']/a/text()").extract()[-2]
if number < last_number:
new_url = 'http://news.hfut.edu.cn/list-28-%d.html' % (number + 1)
yield scrapy.Request(new_url, callback=self.parse)
else:
return
def parse(self, response):
messages = response.xpath("//table[@class='winstyle54630']").xpath(
".//tr[@height='26']")
for i in xrange(len(messages)):
report_name = messages[i].xpath(".//td")[0].xpath(
".//a/text()").extract()[0]
if u'学术报告' not in report_name:
continue
report_url = self.domain + messages[i].xpath(".//td")[0].xpath(
".//a/@href").extract()[0][3:]
report_time = get_localtime(messages[i].xpath(".//td")[1].xpath(
".//span/text()").extract()[0].strip().replace('/', '-'))
if report_time > end_time:
continue
if report_time < now_time:
return
yield scrapy.Request(report_url,
callback=self.parse_pages,
meta={
'link': report_url,
'number': i + 1
})
# return
now_number = int(
response.xpath("//tr[@valign='middle']/td/text()").extract()
[0].strip().split('/')[0][-1])
last_number = int(
response.xpath("//tr[@valign='middle']/td/text()").extract()
[0].strip().split('/')[-1])
def parse(self, response):
messages = response.xpath("//ul[@class='list-none metlist']/li")
print_new_number(self.counts, 'USTC', self.name)
for i in xrange(len(messages)):
report_url = self.domain + messages[i].xpath(".//a/@href").extract()[0][2:]
report_time = get_localtime(messages[i].xpath(".//span/text()").extract()[0].strip())
if report_time < now_time:
return
yield scrapy.Request(report_url, callback=self.parse_pages, meta={'link': report_url, 'number': i + 1})
def parse(self, response):
messages = response.xpath("//div[@class='box_list']/ul/li")
for i in xrange(len(messages)):
report_url = self.domain + messages[i].xpath(".//a/@href").extract()[0][1:]
report_time = get_localtime(messages[i].xpath(".//p/text()").extract()[0].strip())
if report_time < now_time:
return
yield scrapy.Request(report_url, callback=self.parse_pages, meta={'link': report_url, 'number': i + 1})
def parse(self, response):
messages = response.xpath("//td[@class='middle']").xpath(".//tr")
print_new_number(self.counts, 'USTC', self.name)
for i in xrange(len(messages)):
report_title = messages[i].xpath(".//span/a/text()").extract()[0]
report_url = self.domain + messages[i].xpath(".//span/a/@href").extract()[0]
report_time = get_localtime(messages[i].xpath(".//span/a/text()").extract()[-1].strip('()'))
if report_time < now_time:
return
if u'本周报告' in report_title:
continue
yield scrapy.Request(report_url, callback=self.parse_pages, meta={'link': report_url, 'number': i + 1})
def parse(self, response):
links = response.xpath("//li[@width='30%']/a/@href").extract()
times = response.xpath("//li[@width='30%']/span/text()").extract()
print_new_number(self.counts, 'USTC', self.name)
l = len(links)
for i in range(l):
report_url = self.domain + links[i][2:]
report_time = get_localtime(times[i])
if report_time < now_time:
return
yield scrapy.Request(report_url, callback=self.parse_pages, meta={'link': report_url, 'number': i + 1})
def parse(self, response):
messages = response.xpath("//div[@class='list']/ul/li")
print_new_number(self.counts, 'USTC', self.name)
for i in xrange(len(messages)):
if u'青年论坛' in messages[i].xpath(".//a/text()").extract()[0]:
report_url = messages[i].xpath(".//a/@href").extract()[0]
else:
report_url = self.domain + messages[i].xpath(".//a/@href").extract()[0][9:]
if 'Colloquium' in report_url:
continue
report_time = get_localtime('20' + messages[i].xpath(".//span/text()").extract()[0].strip('[]'))
if report_time < now_time:
return
yield scrapy.Request(report_url, callback=self.parse_pages, meta={'link': report_url, 'number': i + 1})
def parse(self, response):
messages = response.xpath("//div[@id='container']/dl/dd")
for i in xrange(len(messages)):
report_url = self.domain + messages[i].xpath(
".//a/@href").extract()[0][1:]
report_time = get_localtime(
messages[i].xpath(".//i/text()").extract()[0].split(' ')[0])
if report_time < now_time:
return
yield scrapy.Request(report_url,
callback=self.parse_pages,
meta={
'link': report_url,
'number': i + 1
})
def parse(self, response):
messages = response.xpath("//div[@id='container']/dl/dd")
print_new_number(self.counts, 'WHU', self.name)
for i in xrange(len(messages)):
report_url = self.domain + messages[i].xpath(".//a/@href").extract()[0][1:]
report_time = get_localtime(messages[i].xpath(".//i/text()").extract()[0].split(' ')[0])
if report_time < now_time:
return
yield scrapy.Request(report_url, callback=self.parse_pages, meta={'link': report_url, 'number': i + 1})
now_number = int(response.xpath("//div[@class='page fn_clear']/ul/li[@class='thisclass']/text()").extract()[0])
last_number = int(response.xpath("//span[@class='pageinfo']/strong")[0].xpath(".//text()").extract()[0])
if not (now_number < last_number):
return
new_url = 'http://cs.whu.edu.cn/a/xueshujiangzuofabu/list_39_{}.html'.format(now_number + 1)
yield scrapy.Request(new_url, callback=self.parse)
def parse(self, response):
messages = response.xpath(
"//div[@class='view-content']/table/tbody/tr")
print_new_number(self.counts, 'USTC', self.name)
sign = 0
for i in xrange(len(messages)):
message = messages[i].xpath(".//td")
report_url = self.domain + message[0].xpath(
".//a/@href").extract()[0][1:]
report_class = message[1].xpath(".//text()").extract()[0].strip()
report_time = get_localtime(
message[2].xpath(".//text()").extract()[0].strip())
if u'学术报告' not in report_class:
continue
if report_time < now_time:
sign = 1
continue
yield scrapy.Request(report_url,
callback=self.parse_pages,
meta={
'link': report_url,
'number': i + 1
})
# The report time of this page is not sorted, so we only stop the procedure in the end of a page.
if sign:
return
now_number = response.xpath(
"//ul[@class='pager']/li[@class='pager-current first']/text()"
).extract()
if len(now_number) == 0:
now_number = int(
response.xpath(
"//ul[@class='pager']/li[@class='pager-current']/text()").
extract()[0])
else:
now_number = int(now_number[0])
next_url = 'http://ess.ustc.edu.cn/notice?page=%d' % now_number
yield scrapy.Request(next_url, callback=self.parse)
def parse(self, response):
messages = response.xpath("//td[@class='middle']").xpath(".//tr")
print_new_number(self.counts, 'USTC', self.name)
for i in xrange(len(messages)):
report_title = messages[i].xpath(".//span/a/text()").extract()[0]
report_url = self.domain + messages[i].xpath(".//span/a/@href").extract()[0]
report_time = get_localtime(messages[i].xpath(".//span/a/text()").extract()[-1].strip('()'))
if report_time < now_time:
return
if u'本周报告' in report_title:
continue
yield scrapy.Request(report_url, callback=self.parse_pages, meta={'link': report_url, 'number': i + 1})
now_number = int(response.xpath("//a[@href='#']").xpath(".//text()").extract()[0])
last_number = int(response.xpath("//a[@href='#']").xpath(".//text()").extract()[-1][1:])
if now_number > last_number:
return
next_url = 'http://math.ustc.edu.cn/new/list.php?fid=35&page=%d' % (now_number + 1)
yield scrapy.Request(next_url, callback=self.parse)
def parse_pages(self, response):
messages = response.xpath("//div[@class='bbs-info']")
title = self.try_get_message(messages.xpath(".//h2/text()").extract())
time = messages.xpath(".//p")[0].xpath(".//text()").extract()[1]
address = messages.xpath(".//p")[1].xpath(".//text()").extract()[1]
speaker = messages.xpath(".//p")[2].xpath(".//text()").extract()[1]
other = response.xpath("//div[@class='show-new']")
if len(other) == 0:
content = ''
else:
content = other.xpath(".//text()").extract()[0].strip()
if u'简介：' in content or 'Abstract：' in content or u'简介:' in content or 'Abstract:' in content:
content = self.connect_messages(
content, '：'
) if u'简介：' in content or 'Abstract：' in content else self.connect_messages(
content, ':')
else:
pass
report_time = get_localtime(
response.xpath("//div[@class='wtime']/text()").extract()
[0].strip())
if report_time < now_time:
title = ''
else:
self.counts += 1
print_new_number(self.counts, 'THU', self.name)
all_messages = save_messages('THU', self.name, title, time, address,
speaker, '', content, '',
response.meta['link'],
response.meta['number'], u'清华大学')
return all_messages
def parse(self, response):
messages = response.xpath("//div[@class='full-page-list']/ul/li")
print_new_number(self.counts, 'SYSU', self.name)
for i in xrange(len(messages)):
report_name = messages[i].xpath(".//a/text()").extract()[0]
if u'学术报告：' not in report_name and u'学术报告:' not in report_name:
continue
report_url = self.domains + messages[i].xpath(
".//a/@href").extract()[0][1:]
report_time = get_localtime(
messages[i].xpath(".//span/text()").extract()[0].replace(
'/', '-'))
if report_time < now_time:
return
yield scrapy.Request(report_url,
callback=self.parse_pages,
meta={
'link': report_url,
'number': i + 1
})
def parse(self, response):
messages = response.xpath(
"//div[@class='view-content']/table/tbody/tr")
print_new_number(self.counts, 'USTC', self.name)
sign = 0
for i in xrange(len(messages)):
message = messages[i].xpath(".//td")
report_url = self.domain + message[0].xpath(
".//a/@href").extract()[0][1:]
report_class = message[1].xpath(".//text()").extract()[0].strip()
report_time = get_localtime(
message[2].xpath(".//text()").extract()[0].strip())
if u'学术报告' not in report_class:
continue
if report_time < now_time:
sign = 1
continue
yield scrapy.Request(report_url,
callback=self.parse_pages,
meta={
'link': report_url,
'number': i + 1
})
# -*- coding:utf-8 -*-
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
import time
import scrapy
from Global_function import get_localtime, print_new_number, save_messages
now_time = get_localtime(time.strftime("%Y-%m-%d", time.localtime()))
# now_time = 20170401
class USTC006_Spider(scrapy.Spider):
name = 'USTC006'
start_urls = ['http://biox.ustc.edu.cn/xsbg/']
domain = 'http://biox.ustc.edu.cn/xsbg/'
counts = 0
def parse(self, response):
messages = response.xpath("//ul[@class='list-none metlist']/li")
print_new_number(self.counts, 'USTC', self.name)
for i in xrange(len(messages)):
report_url = self.domain + messages[i].xpath(".//a/@href").extract()[0][2:]
report_time = get_localtime(messages[i].xpath(".//span/text()").extract()[0].strip())
if report_time < now_time:
return
yield scrapy.Request(report_url, callback=self.parse_pages, meta={'link': report_url, 'number': i + 1})
# return
