def generateTempitemForGet(self, response):
parsed = urlparse.urlparse(response.url)
parameters = urlparse.parse_qs(parsed.query)
item = ProjectItem()
url = parsed.geturl()
if "?" in url:
item['url'] = url[:url.find('?')]
else:
item['url'] = url
item['param'] = parameters
item['type'] = "GET"
if self.login_required:
item["loginrequired"] = "true"
item["loginurl"] = self.login_url
else:
item["loginrequired"] = "false"
item["loginurl"] = ""
referer = None
if "Referer" in response.request.headers.keys():
referer = response.request.headers["Referer"]
item["headers"] = {
"referer": referer,
"user-agent": response.request.headers["User-Agent"]
}
return item
def parse(self, response):
part = response.meta['part']
# inspect_response(response, self)
for li in response.xpath('//ul[@class="for-list"]/li')[1:2]:
item = ProjectItem()
item['part'] = part
item['title'] = li.xpath('div[@class="titlelink box"]/a[@class="truetit"]//text()').get().strip().replace(
'\n', ' ')
href = li.xpath('div[@class="titlelink box"]/a[@class="truetit"]/@href').get()
item['href'] = 'https://bbs.hupu.com' + href
item['id'] = re.search(r'\d+', href).group()
item['author'] = li.xpath('div[@class="author box"]/a[@class="aulink"]/text()').get()
item['reply_count'] = li.xpath('span[@class="ansour box"]/text()').get().split('\xa0')[0]
item['view_count'] = li.xpath('span[@class="ansour box"]/text()').get().split('\xa0')[-1]
link_count_text = li.xpath('div[@class="titlelink box"]/span[@class="light_r "]/a/@title').get()
if link_count_text:
link_count = re.search(r'\d+', link_count_text).group()
else:
link_count = 0
item['link_count'] = link_count
item['comment'] = []
# yield item
total_page = (int(item['reply_count']) - 1) // 20 + 1
print('{},{},{},{},{},{},{}, 总页数:{}'.format(item['id'], item['href'], item['title'], item['author'],
item['reply_count'], item['view_count'], item['link_count'],
total_page))
if item['reply_count'] != '0':
yield scrapy.Request('https://m.hupu.com/api/bbs/replies/{}-1'.format(item['id']),
meta={'item': item, 'total_page': total_page, 'page': 1},
callback=self.comment)
def parse_items(self, response):
item = ProjectItem()
item['url'] = response.url
item['text'] = self.get_text(response)
domain = self.get_domain(response.url)
item['unique_id'] = self.domain_to_id[domain]
item['depth'] = response.request.meta['depth'] # uses DepthMiddleware
print("Depth: ", item['depth'])
yield item
def parse(self, response):
item = ProjectItem()
item['Confirmed'] = response.xpath(
'/html/body/section[1]/div/div[1]/div[1]/text()').extract_first()
item['Suspected'] = response.xpath(
'/html/body/section[1]/div/div[2]/div[1]/text()').extract_first()
item['Healing'] = response.xpath(
'/html/body/section[1]/div/div[3]/div[1]/text()').extract_first()
item['Death'] = response.xpath(
'/html/body/section[1]/div/div[4]/div[1]/text()').extract_first()
item['Deadline'] = response.xpath(
'/html/body/section[1]/p[1]/text()').extract_first()[3:]
yield item
def parse_item(self, response):
i = 0
for quote in response.css('article'):
if i == 0:
item = ProjectItem()
file_url = quote.css(
'a[data-entity-type="file"]::attr(href)').get()
file_url = response.urljoin(file_url)
item['file_urls'] = [file_url]
item['file_names'] = file_url.split("/")[-1]
i += 1
yield item
def generateLoginItem(self, form_data, action):
self.login_url = action
ItemPost = ProjectItem()
ItemPost["url"] = self.login_url
output_form_data = {}
for key in form_data.keys():
output_form_data[key] = [form_data[key]]
ItemPost["param"] = output_form_data
ItemPost["type"] = "POST"
ItemPost["loginrequired"] = "false"
ItemPost["loginurl"] = ""
return ItemPost
def generate_login_item(self, form_data, action):
self.login_url = action
post_item = ProjectItem()
post_item["url"] = self.login_url
output_form_data = {}
for key in form_data.keys():
output_form_data[key] = [form_data[key]]
post_item["param"] = output_form_data
post_item["type"] = "POST"
post_item["loginrequired"] = "false"
post_item["loginurl"] = ""
return post_item
def parse(self, response):
# title = scrapy.Field() #定义标题
# week = scrapy.Field() #定义星期
# img = scrapy.Field() #定义图片
# temp = scrapy.Field() #定义温度
# rain = scrapy.Field() #定义降雨
# wind = scrapy.Field() #定义风力
# 过滤出包含六天天气的html代码,后续在用于循环
sixday_detail = response.xpath('//div[@class="tqshow1"]')
# 定义items,用于存储六天的天气信息
items = []
# 循环每天的天气信息，并提取指定信息
for day in sixday_detail:
# 调用item.py的ProjectItem()类来实例化一个item
item = ProjectItem()
# 提取标题,并循环成str
datetitle = ''
for date in day.xpath('./h3//text()').extract():
datetitle += date
item['title'] = datetitle
# 提取星期,返回为list，加入[0]下标获得第一个值
item['week'] = day.xpath('./p//text()').extract()[0]
# 提取图片,返回为list，加入[0]下标获得第一个值
item['img'] = day.xpath(
'./ul/li[@class="tqpng"]/img/@src').extract()[0]
# 提取温度,并循环成str
templist = ''
for temprange in day.xpath('./ul/li[2]//text()').extract():
templist += temprange
item['temp'] = templist
# 提取降雨,返回为list，加入[0]下标获得第一个值
item['rain'] = day.xpath('./ul/li[3]//text()').extract()[0]
# 提取风力,返回为list，加入[0]下标获得第一个值
item['wind'] = day.xpath('./ul/li[4]//text()').extract()[0]
#把item存入items列表
items.append(item)
print '----------------bye from spider------------------------'
return items
def generate_post_item(self, post_form):
post_item = ProjectItem()
post_item["url"] = post_form["url"]
post_item["param"] = post_form["fields"]
post_item["type"] = "POST"
if self.login_required:
post_item["loginrequired"] = "true"
post_item["loginurl"] = self.login_url
else:
post_item["loginrequired"] = "false"
post_item["loginurl"] = ""
if bool(post_item["param"]):
return post_item
return None
def start_requests(self):
# for part, link in parts.items():
# open('results/{}.txt'.format(part), 'w').close()
# for i in range(2, 3): # 爬前十页
# yield scrapy.Request('https://bbs.hupu.com/rockets-{}'.format(i), meta={'part': '火箭专区'})
# yield scrapy.Request('https://bbs.hupu.com/26073334.html', meta={'part': '火箭专区'}, callback=self.comment())
item = ProjectItem()
item['id'] = '26073334'
item['comment'] = []
item['part'] = '火箭专区'
item['title'] = '【一图流】哈登压哨后撤三分命中'
item['author'] = 'LonzoBa'
item['reply_count'] = 0
item['link_count'] = 0
item['view_count'] = 0
yield scrapy.Request('https://m.hupu.com/api/bbs/replies/26073334-1',
meta={'item': item, 'total_page': 1, 'page': 1},
callback=self.comment)
def generatePostItem(self, post_form):
ItemPost = ProjectItem()
ItemPost["url"] = post_form["url"]
ItemPost["param"] = post_form["fields"]
self.log(55555555555555555555555555555555555555555)
self.log(post_form["isGet"])
if (post_form["isGet"]):
ItemPost["type"] = "GET"
else:
ItemPost["type"] = "POST"
if self.login_required:
ItemPost["loginrequired"] = "true"
ItemPost["loginurl"] = self.login_url
else:
ItemPost["loginrequired"] = "false"
ItemPost["loginurl"] = ""
if bool(ItemPost["param"]):
return ItemPost
return None
def generateTempitemForGetNoResp(self, response_url):
parsed = urlparse.urlparse(response_url)
parameters = urlparse.parse_qs(parsed.query)
item = ProjectItem()
url = parsed.geturl()
if "?" in url:
item['url'] = url[:url.find('?')]
else:
item['url'] = url
item['param'] = parameters
item['type'] = "GET"
if self.login_required:
item["loginrequired"] = "true"
item["loginurl"] = self.login_url
else:
item["loginrequired"] = "false"
item["loginurl"] = ""
item["headers"] = {}
return item
def parse_new_page(self, response):
# print(response.text)
link_address='';
content_word='';
title=response.css('.show_con_title ::text').extract()[0]
data=response.css('.show_con_info em:nth-child(1)::text').extract()[0][-19:-1]
extence=response.css('.show_con_info em:nth-child(3)::text').extract()[0]
content=response.css('.show_con_box p::text').extract()
link=response.css('.show_con_box a[href^="http"]::attr(href) ').extract()
for link_item in link:
if link_item.find(".doc")!= -1 or link_item.find(".xls")!=-1 or link_item.find(".xlsx")!= -1:
link_address=link_address+link_item+';'
for content_item in content:
if content_item.find("报名方式")!=-1 or content_item.find("应聘方法")!=-1 or content_item.find("报名时间")!=-1 or content_item.find("资格条件")!=-1:
content_word=content_word+content_item+' :'
item=ProjectItem()
item['title']=title
item['data']=data
item['extence'] = extence
item['content'] = content_word
item['link'] = link_address
yield item
def parseHtml(self, response):
# 每个职位的节点对象列表
baseList = response.xpath('//tr[@class="odd"] | //tr[@class="even"]')
for base in baseList:
item = ProjectItem()
item["PositionName"] = base.xpath('./td[1]/a/text()').extract()[0]
# 链接
item["PositionLink"] = base.xpath('./td[1]/a/@href').extract()[0]
# 类别
item["PositionType"] = base.xpath('./td[2]/text()').extract()
if item["PositionType"]:
item["PositionType"] = item["PositionType"][0]
else:
item["PositionType"] = "无"
# 人数
item["PositionNum"] = base.xpath('./td[3]/text()').extract()[0]
# 地点
item["PositionAddress"] = base.xpath('./td[4]/text()').extract()[0]
# 时间
item["PositionTime"] = base.xpath('./td[5]/text()').extract()[0]
yield item
def parse(self, response):
yield ProjectItem(name='updated_item', index=1, last=self.last)
yield ProjectItem(name='new_item', index=1)
def parse(self, response):
#提取每个response的数据
node_list = response.xpath("//div[@class='dw_table']/div[@class='el']")
total_page_pig = response.xpath("//span[@class = 'td']/text()")
#正则表达式提取页数
pattern1 = re.compile(r"(?<=共).+?(?=页，)") #我们在编译这段正则表达式
matcher1 = re.search(pattern1,
r"" + str(total_page_pig)) #在源文本中搜索符合正则表达式的部分
total_page = (matcher1.group(0)) #页数
print(total_page)
for node in node_list:
# 新建一个item
item = ProjectItem()
print('进入！！')
item['position_name'] = node.xpath("./p/span/a/@title").extract()[
0] #返回list中的第一个元素 职位
item['posttion_place'] = node.xpath(
"./span[1]/a/text()").extract()[0] #公司
item['posttion_led'] = node.xpath("./span[2]/text()").extract()[
0] #地点
if len(node.xpath("./span[3]/text()")):
item['position_department'] = node.xpath(
"./span[3]/text()").extract()[0] #薪资
else:
item['position_department'] = '空'
item['positon_time'] = node.xpath("./span[4]/text()").extract()[
0] #时间
item['position_info'] = node.xpath("./span[1]/a/@href").extract()[
0] #网址
print('1')
yield item
# s = (response.xpath("//li[@class='bk']/a/@href")).extract()[0]
# print('\n\n\n\n\n\n',type(s),'\n',s,'\n\n\n\n\n\n\n')
# s = (response.xpath("//li[@class='bk']/a/@href")).extract()[1]
# print('\n\n\n\n\n\n',type(s),'\n',s,'\n\n\n\n\n\n\n')
#打印当前页数
print(
'\n\n\n\n\n\n',
str(
response.xpath(
"//div[@class = 'p_in']/ul/li[@class='on']/text()").
extract()[0]), '\n\n\n\n\n\n\n')
# #判断当前页是不是最后一页
if str(
response.xpath(
"//div[@class = 'p_in']/ul/li[@class='on']/text()").
extract()[0]) != total_page:
if str(
response.xpath(
"//div[@class = 'p_in']/ul/li[@class='on']/text()").
extract()[0]) == '1':
url = (
response.xpath("//li[@class='bk']/a/@href")).extract()[0]
yield scrapy.Request(url, callback=self.parse)
else:
url = (
response.xpath("//li[@class='bk']/a/@href")).extract()[1]
# print('\n\n\n\n\n',url,'\n\n\n\n\n\n')
yield scrapy.Request(url, callback=self.parse)
