def parse_url(self, response):
html = Selector(response)
id = html.xpath(
"//ul[@class= 'bigimg cloth_shoplist']/li/@id").extract()
next_link = html.xpath(
"//*[@id='12810']/div[3]/div[2]/div/ul/li/a[@title='下一页']/@href"
).extract_first()
start_url = 'http://product.dangdang.com/'
next_start_url = 'http://category.dangdang.com'
item = response.meta['item']
atype = item['atype']
item = DangdangItem(atype=atype)
for aid in id:
item['aid'] = int(aid)
item = DangdangItem(aid=aid, atype=atype)
item_url = start_url + aid + '.html'
yield scrapy.Request(url=item_url,
callback=self.parse_item,
headers=self.header,
meta={'item': item})
if next_link != '':
next_url = next_start_url + next_link
yield scrapy.Request(url=next_url,
callback=self.parse_url,
headers=self.header,
meta={'item': item})
def parse(self, response):
for atype in range(0, 3):
item = DangdangItem()
item['atype'] = atype
item = DangdangItem(atype=atype)
cid = "-cid400252" + str(atype) + ".html"
base_url = "http://category.dangdang.com/pg1" + cid
yield scrapy.Request(url=base_url,
callback=self.parse_url,
headers=self.header,
meta={'item': item})
def parse(self, response):
lilist = response.css('ul.bigimg li')
#print(lilist)
for li in lilist:
item = DangdangItem()
title = li.css('a::attr(title)').extract_first()
if len(title) > 32:
item['title'] = title[:32]
else:
item['title'] = title
item['author'] = li.css('p.search_book_author span a::text').extract_first()
item['price'] = li.css('p.price span::text').extract_first()
item['comment_num'] = li.css('p.search_star_line a::text').extract_first()[:-3]
item['detail'] = li.css('p.detail::text').extract_first()
if li.css('a img::attr(data-original)').extract_first():
item['picurl'] = li.css('a img::attr(data-original)').extract_first()
else:
item['picurl'] = li.css('a img::attr(src)').extract_first()
item['picurl'] = item['picurl'].replace('_b_','_w_')
yield item
#print(item)
time.sleep(3)
self.p += 1
if self.p < 6:
next_url = 'http://search.dangdang.com/?key=python&page_index='+str(self.p)
url = response.urljoin(next_url)
yield scrapy.Request(url=url,callback=self.parse)
def parse(self, response):
all_data_x = response.xpath('//div[@class="con flq_body"]')[0]
all_first_title = all_data_x.xpath('./div[contains(@class,"level_one")]')
for first_title_e in all_first_title:
f = first_title_e.xpath('./dl/dt/text()').extract_first()
if f is not None:
item = DangdangItem()
f = re.sub(r'\r|\n|\t| ','',f)
if not f:
f = first_title_e.xpath('./dl/dt/a/text()').extract()
f = ''.join(f)
f = re.sub(r'\r|\n|\t| ','',f)
item['first_title'] = f
all_s_t_title = first_title_e.xpath('.//div[@class="col eject_left"]/dl')
if all_s_t_title.extract_first() is not None:
for s_t in all_s_t_title:
second_title = s_t.xpath('./dt/text()').extract_first()
second_title = re.sub(r'\r|\n|\t| ','',second_title)
if second_title:
item['second_title'] = second_title
else:
item['second_title'] = s_t.xpath('./dt/a/text()').extract_first()
item['second_title'] = item['second_title'].replace(' ','')
all_third_title = s_t.xpath('./dd/a')
for third_e in all_third_title:
item['third_title'] = third_e.xpath('./@title').extract_first()
item['label_url'] = third_e.xpath('./@href').extract_first()
if ('search.dangdang.com' in item['label_url']) or ('category.dangdang.com' in item['label_url']):
item_copy = copy.deepcopy(item)
yield scrapy.Request(item_copy['label_url'],callback=self.parse_book_detail,meta={'item':item_copy})
def parse_item(self, response):
item_html = Selector(response)
item = DangdangItem()
item = response.meta['item']
shop_name = item_html.xpath(
"//*[@id='service-more']/div[2]/p[1]/span/span[2]/a/text()"
).extract_first()
item['shop_name'] = shop_name
item_name = ','.join(
item_html.xpath(
"//*[@id='product_info']/div[1]/h1/text()").extract()).replace(
' ', '').replace('\r\n', '')
item['item_name'] = item_name
item_price = ','.join(
item_html.xpath("//*[@id='dd-price']/text()").extract()).replace(
' ', '').replace(',', '')
item['item_price'] = item_price
item_from = ','.join(
item_html.xpath(
"//*[@id='shop-geo-name']/text()").extract()).replace(
' 至', '')
item['item_from'] = item_from
image_url = item_html.xpath(
"//*[@id='main-img-slider']/li/a/@data-imghref").extract()
item['image_url'] = image_url
image_list = ','.join(image_url)
item['image_list'] = image_list
yield item
def parse(self, response):
'''
递归解析响应数据
'''
print('*'*64)
dlist = response.selector.xpath(".//ul[@class='bigimg']/li")
for dd in dlist:
item = DangdangItem()
item['name'] = dd.xpath("./a/@title").extract_first() #good
price = dd.xpath(".//span[@class='search_now_price']").extract_first()
price = re.findall(".*?([0-9]*\.[0-9]*)",price)
if(price[0]):
item['price'] = price[0]
else:
item['price'] = None
item['pic'] = dd.xpath(".//img/@data-original|.//img/@src").extract_first()
item['author'] = dd.xpath(".//a[@name='itemlist-author']/@title").extract_first()
item['publisher'] = dd.xpath(".//a[@name='P_cbs']/text()").extract_first() #good
item['comments'] = dd.xpath(".//a[@class='search_comment_num']/text()").extract_first() #wrong
item['pubdate'] = dd.re_first("(([0-9]{4})-([0-9]{2})-([0-9]{2}))") #good
item['description'] = dd.xpath(".//p[@class='detail']/text()").extract_first() # good
yield item
self.p += 1
# 想爬取多少页？
if(self.p<=10):
next_url = "http://search.dangdang.com/?key=python&act=input&page_index=" + str(self.p)
url = response.urljoin(next_url)
yield scrapy.Request(url=url, callback=self.parse)
def parse(self, response):
item = DangdangItem()
item['title'] = response.xpath("//a[@class ='pic']/@title").extract()
item['link'] = response.xpath("//a[@class ='pic']/@href").extract()
item['comment'] = response.xpath("//a[@class ='search_comment_num']/text()").extract()
yield item
for i in range(2,101):
url = "http://category.dangdang.com/pg"+str(i)+"-cp01.54.06.00.00.00.html"
yield Request(url,callback=self.parse)
def parse(self, response):
item = DangdangItem()
item["title"] = response.xpath("//a[@name='itemlist-picture']/@title").extract()
item["link"] = response.xpath("//a[@name='itemlist-picture']/@href").extract()
item["comment"] = response.xpath("//a[@name='itemlist-review']/text()").extract()
yield item
for i in range(2,81):
url = "http://category.dangdang.com/pg"+str(i)+"-cid4008154.html"
yield Request(url,callback=self.parse)
def parse(self, response):
item = DangdangItem() #items.py里面的函数
item["title"] = response.xpath("//a[@class='pic']/@title").extract()
item["link"] = response.xpath("//a[@class='pic']/@href").extract()
item["comment"] = response.xpath("//a[@name='itemlist-review']/text()").extract()
yield item
for i in range(2, 10):
url = "http://category.dangdang.com/pg"+str(i)+"-cp01.54.06.00.00.00.html"
yield Request(url, callback = self.parse)
def handle_items(self, response):
item = DangdangItem()
item["title"] = response.xpath(
"//a[@name='sort-big-pic']/@title").extract()
item["link"] = response.xpath(
"//a[@name='sort-big-pic']/@href").extract()
item["comment"] = response.xpath(
"//a[@name='sort-evaluate']/text()").extract()
yield item
def parse(self, response):
item=DangdangItem()
item["title"]=response.xpath("//a[@name='sort-big-pic']/@title").extract()
item["link"]=response.xpath("//a[@name='sort-big-pic']/@href").extract()
item["comment"]=response.xpath("//a[@name='sort-evaluate']/text()").extract()
yield item
for i in range(2,81):
url='http://category.dangdang.com/pg'+str(i)+'-cid4008154.html'
yield Request(url,callback=self.parse)
def parse_name(self, response):
items = DangdangItem()
items['title'] = response.xpath(
'//div[@class="name_info"]/h1/@title').extract()
items['num'] = response.xpath(
'//a[@id="comm_num_down"]/text()').extract()
items['link'] = response.url
items['price'] = response.xpath('//p[@id="dd-price"]/text()').extract()
yield items
def parse(self, response):
item = DangdangItem()
item['title'] = response.xpath("//a[@class='pic']/@title").extract
item['link'] = response.xpath("//a[@class='pic']/@href").extract
item['comment'] = response.xpath(
"//a[@class='search_comment_num']/text()").extract
print(item['title'])
print(item['link'])
print(item['comment'])
yield item
def get_info(self, response):
item = DangdangItem()
item['name'] = response.xpath('//a[@class="pic"]/@title').extract()
item['price'] = response.xpath(
'//p[@class="price"]/span/text()').extract()
item["link"] = response.xpath("//a[@class='pic']/@href").extract()
item["comnum"] = response.xpath(
"//a[@name='itemlist-review']/text()").extract()
#print('11111111111111111111')
yield item
def parse_item(self, response):
lst = response.xpath('//ul[@class="bigimg cloth_shoplist"]/li')
for i in lst:
item = DangdangItem()
item['name'] = i.xpath('./p[@class="name"]/a/@title').extract()[0]
item['price'] = i.xpath(
'./p[@class="price"]/span/text()').extract()[0][1:]
item['link'] = i.xpath('./p[@class="link"]/a/@href').extract()[0]
item['comment'] = i.xpath(
'./p[@class="star"]/a/text()').extract()[0].replace('条评论', '')
yield item
def parse(self, response):
item = DangdangItem()
item["title"] = response.xpath("//a[@name='itemlist-picture']/@title").extract()
item["link"] = response.xpath("//a[@name='itemlist-picture']/@href").extract()
item["price"] = response.xpath("//span[@class='price_n']/text()").extract()
item["comment"] = response.xpath("//a[@name='itemlist-review']/text()").extract()
# print(item["title"])
yield item
for i in range(2, 20):
url = 'http://search.dangdang.com/?key=%CC%A4%B2%BD%BB%FA&page_index=' + str(i)
yield Request(url, callback=self.parse)
def parse(self, response):
html = response.text
tree = etree.HTML(html)
li_list = tree.xpath('//*[@id="component_59"]/li')
for li in li_list:
item = DangdangItem()
item['title'] = li.xpath('./a/@title')
item['miaoshu'] = li.xpath('./p[@class = "detail"]/text()'
) # 之前的爬虫写错了导致抓到的title和miaoshu放在一个了
# print(li)
print(item['title'])
yield item
def parse_name(self, response):
items = DangdangItem()
items['title'] = response.xpath(
'//*[@id="product_info"]/div[1]/h1/@title').extract()
items['num'] = response.xpath(
'//*[@id="comm_num_down"]/text()').extract()
items['link'] = response.url
items['price'] = response.xpath('//*[@id="dd-price"]/text()').extract()
items['cbs'] = response.xpath(
'//*[@id="product_info"]/div[2]/span[2]/a/text()').extract()
items['pic'] = response.xpath('//*[@id="largePic"]/@src').extract()
yield items
def parse_subpage(self,response,category):
length= len(response.xpath('//*[@id="component_0__0__8395"]/li/a/img').extract())#获取每一面的图书数量
for i in range(0,length+1):
item = DangdangItem()
item['name']=response.xpath('//*[@id = "component_0__0__8395"] /li[{}]/p[2]/a/text()'.format(i)).extract()
item['author']=response.xpath('//*[@id="component_0__0__8395"]/li[{}]/p[5]/text()'.format(i)).extract()
item['price']=response.xpath('//*[@id="component_0__0__8395"]/li[{}]/p[1]/span[1]/text()'.format(i)).extract()
item['comments']=response.xpath('//*[@id="component_0__0__8395"]/li[{}]/p[4]/a/text()'.format(i)).extract()
item['category']=category
yield item
def parse(self, response):
item = DangdangItem()
item['title'] = response.xpath(
'//a[@name="itemlist-picture"]/@title').extract()
item['link'] = response.xpath(
'//a[@name="itemlist-picture"]/@href').extract()
item['comment'] = response.xpath(
'//a[@class="search_comment_num"]/text()').extract()
yield item
for i in range(1, 100):
url = 'http://search.dangdang.com/?key=%BC%C6%CB%E3%BB%FA&act=input&page_index=' + str(
i)
yield Request(url, callback=self.parse)
def parse(self, response):
item = DangdangItem()
item["name"] = response.xpath("//h1/@title").extract_first()
item["author"] = response.xpath(
"//span[@id='author']/a[1]/text()").extract_first()
item["price"] = response.xpath(
"//p[@id='dd-price']/text()[2]").extract_first()
item["ISBN"] = response.xpath(
"//div[@id='detail_describe']/ul/li[5]/text()").extract_first()
item["crawl_time"] = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
self.number = self.number + 1
item["id"] = self.number
yield item
def parse(self, response):
item = DangdangItem()
item['name'] = response.xpath('//*[@class="pic"]/@title').extract()
item['price'] = response.xpath(
'//*[@class="price_n"]/text()').extract()
item['link'] = response.xpath('//*[@class="pic"]/@href').extract()
item['comment'] = response.xpath(
'//*[@dd_name="单品评论"]/text()').extract()
yield item
for i in range(2, 5):
url = 'http://category.dangdang.com/pg{}-cid4005627.html'.format(i)
yield Request(url, callback=self.parse)
def parse(self, response):
item = DangdangItem()
item['title'] = response.xpath(
'//a[@name="itemlist-title"]/@title').extract()
item['link'] = response.xpath(
'//a[@name="itemlist-title"]/@href').extract()
item['comment'] = response.xpath(
'//a[@class="search_comment_num"]/text()').extract()
yield item
for i in range(2, 101):
url = 'http://category.dangdang.com/pg' + str(
i) + '-cp01.54.06.00.00.00.html'
yield Request(url, callback=self.parse)
def parse(self, response):
#print(response.text)
tmp = response.xpath("//div[@id='bd']//li[@id]") #选取中商品
# print(type(tmp))
print(len(tmp))
for li in tmp:
item = DangdangItem()
item['book_name'] = li.xpath('p[@name]/a/@title').extract_first()
item['price'] = li.xpath(
"p[@class='price']/span[@class='search_now_price']/text()"
).extract_first()
#print(item['price'])
item['author'] = li.xpath(
"p[@class='search_book_author']/span[1]/a[1]/@title"
).extract_first()
item['pubdate'] = li.xpath(
"p[@class='search_book_author']/span[2]/text()").extract_first(
)
item['press'] = li.xpath(
"p[@class='search_book_author']/span[3]/a[1]/@title"
).extract_first()
item['star'] = li.xpath(
"p[@class='search_star_line']/span/span/@style").extract_first(
)
item['_id'] = li.xpath("a/@href").extract_first()
item['comment'] = li.xpath("p[@class='search_star_line']/a/text()"
).extract_first() #a/@href可以提取到评论的连接
item['comment_url'] = li.xpath(
"p[@class='search_star_line']/a/@href").extract_first(
) # a/@href可以提取到评论的连接
#print(item['comment_url'])
#print(item['star'],item['book_url'])
#print(item['author'],item['press'],item['pubdate'])
yield item
# next = tmp.xpath("//li[@class='next']/a/@href")
#print(next)
# if next:
# print("http://category.dangdang.com"+next.extract_first())
# yield scrapy.Request("http://category.dangdang.com"+next.extract_first(),callback=self.parse)
#书名 // li[ @ sku] / p[ @ name]
#价格//li[@sku]/p[@class='price']/span[@class='search_now_price'] 有折扣的情况下，无折扣饿另说
#作者，出版社//li[@sku]/p[@class='search_book_author']/span/a[1]/@title
#星级//li[@sku]/p[@class='search_star_line']/span/span/@style width: 90%;
#//li[@sku]/p[@class='search_star_line']/a 1232312条评论 评论数
#//评论网址//li[@sku]/p[@class='search_star_line']/a/@href
#出版日期//li[@sku]/p[@class='search_book_author']/span[2] /2013-01-01
def parse_page(self, response):
for item in response.xpath(
'//*[@id="search_nature_rg"]/ul[@class="bigimg"]/li'):
# 所有图书
book = DangdangItem()
# try:
book['price'] = float(
item.xpath('./p[@class="price"]/span[1]/text()').pop().extract(
).lstrip('¥'))
book['type_tag'] = response.meta['type']
book['name'] = item.xpath(
'./p[@class="name"]/a/text()').pop().extract().strip()
book['book_tag'] = str(time.time()) + book.get('name', None)
# book['image_url'] = item.xpath('./a/img/@src').pop().extract()
book['link'] = item.xpath('./p[1]/a/@href').pop().extract()
book['star_level'] = \
int(item.xpath('./p[@class="search_star_line"]/span/span/@style').pop().extract().split(' ')[-1].rstrip(
'%;'))
try:
book['time'] = item.xpath(
'./p[@class="search_book_author"]/span[2]/text()').pop(
).extract().split('/')[-1]
book['author_tag'] = ','.join(
item.xpath(
'./p[@class="search_book_author"]/span[1]/a/text()').
extract()).strip()
book['publish_company'] = item.xpath(
'./p[@class="search_book_author"]/span[3]/a/text()').pop(
).extract().strip()
book['brief'] = item.xpath(
'./p[2]/text()').pop().extract().strip()
except:
scrapy.Spider.log(
self, "Error:{} , url {}:".format(book['name'],
response.url))
finally:
yield book
def parse(self, response):
item = DangdangItem()
item["title"] = response.xpath("//a[@class='pic']/@title").extract()
item["link"] = response.xpath("//a[@class='pic']/@href").extract()
item["comment"] = response.xpath(
"//a[@class='search_comment_num']/text()").extract()
item["price"] = response.xpath(
"//p[@class='price']/span[@class='search_now_price']/text()"
).extract()
yield item
for i in xrange(1, 101):
url = "http://category.dangdang.com/pg" + str(
i) + "-cp01.54.06.00.00.00.html"
yield Request(url, callback=self.parse)
def parse(self, response):
item = DangdangItem()
item["title"] = response.xpath(
"//a[@name='itemlist-title']/@title").extract()
item["link"] = response.xpath(
"//a[@name='itemlist-title']/@href").extract()
item["comment"] = response.xpath(
"//a[@name='itemlist-review']/text()").extract()
# print(item["title"])
yield item
for i in range(2, 11): #爬取2~10页
url = 'http://category.dangdang.com/pg' + str(
i) + '-cid4008154.html'
yield Request(url, callback=self.parse)
def parse(self, response):
lst = response.xpath('//ul[@class="bigimg cloth_shoplist"]/li')
for i in lst:
item = DangdangItem()
item['name'] = i.xpath('./p[@class="name"]/a/@title').extract()[0]
item['price'] = i.xpath(
'./p[@class="price"]/span/text()').extract()[0][1:]
item['link'] = i.xpath('./p[@class="link"]/a/@href').extract()[0]
item['comment'] = i.xpath(
'./p[@class="star"]/a/text()').extract()[0].replace('条评论', '')
yield item
for i in range(2, 5):
url = 'http://category.dangdang.com/pg{}-cid4005627.html'.format(i)
yield Request(url, callback=self.parse)
def parse(self, response):
# hax = Selector(response)
items = []
titles = response.xpath(
'//body//div[@id="search_nature_rg"]//a/@href').extract()
for index in range(len(titles)):
item = DangdangItem()
title = titles[index]
item['links'] = title
items.append(item)
for item in items:
yield FormRequest(dont_filter=True,
url=item['links'],
meta={'item': item},
callback=self.parse2)
def parse_item(self, response):
item = DangdangItem()
item['kind'] = response.xpath(
"//div[@class='layout_location']/span[last()]/text()"
).extract_first()
allitem = response.css('.bang_list.clearfix.bang_list_mode>li')
for i in allitem:
item['name'] = i.css('.name>a').xpath('./@title').extract_first()
item['link'] = i.css('.name>a').xpath('./@href').extract_first()
item['comment'] = i.css('.star>a::text').extract_first()
item['satisfaction'] = i.css('.tuijian::text').extract_first()
item['price'] = i.xpath(
"//div[@class='price']/p[1]/span[@class='price_n']/text()"
).extract_first()
yield item
