def parse(self, response):
# 获取所有图片的a标签
allPics = response.xpath('//div[@class="img"]/a')
for pic in allPics:
# 提取每张图片信息
item = PicItem()
name = pic.xpath('./img/@alt').extract()[0]
addr = pic.xpath('./img/@src').extract()[0]
addr = 'http://www.xiaohuar.com' + addr
item['name'] = name
item['addr'] = addr
# print (item)
# 返回爬取数据
yield item
# 获取下一页
# self.fetchNext(response)
navPageList = response.xpath(
'//div[@id="page"]/div[@class="page_num"]/a')
# print(navPageList)
for navPage in navPageList:
txt = navPage.xpath('./text()').extract()[0]
url = navPage.xpath('./@href').extract()[0]
# print(txt)
if txt == '下一页':
print(url)
yield scrapy.Request(url, callback=self.parse)
break
def parse(self, response):
# 当页面以list开头才进行爬取
if response.url.startswith('http://www.xiaohuar.com/list-'):
# 获取所有图片的a标签
allPics = response.xpath('//div[@class="img"]/a')
for pic in allPics:
# 分别处理每个图片，取出名称及地址
item = PicItem()
name = pic.xpath('./img/@alt').extract()[0]
addr = pic.xpath('./img/@src').extract()[0]
addr = 'http://www.xiaohuar.com' + addr
item['name'] = name
item['addr'] = addr
# 返回爬取到的数据
yield item
# 获取所有的a标签的urls
urls = response.xpath('//a/@href').extract()
for url in urls:
if url.startswith("http://www.xiaohuar.com/list-"):
# url是否在url_set集合中
if url not in XhSpider.url_set:
# 添加url到集合中
XhSpider.url_set.add(url)
# 抛出url
yield self.make_requests_from_url(url)
def parse(self, response):
# 如果图片地址以http://www.xiaohuar.com/list-开头，我才取其名字及地址信息
if response.url.startswith("http://www.xiaohuar.com/list-"):
allPics = response.xpath('//div[@class="img"]/a')
for pic in allPics:
# 分别处理每个图片，取出名称及地址
item = PicItem()
name = pic.xpath('./img/@alt').extract()[0]
addr = pic.xpath('./img/@src').extract()[0]
addr = 'http://www.xiaohuar.com' + addr
item['name'] = name
item['addr'] = addr
# 返回爬取到的信息
yield item
# 获取所有的地址链接
urls = response.xpath("//a/@href").extract()
for url in urls:
# 如果地址以http://www.xiaohuar.com/list-开头且不在集合中，则获取其信息
if url.startswith("http://www.xiaohuar.com/list-"):
if url in XhSpider.url_set:
pass
else:
XhSpider.url_set.add(url)
# 回调函数默认为parse,也可以通过from scrapy.http import Request来指定回调函数
# from scrapy.http import Request
# Request(url,callback=self.parse)
yield self.make_requests_from_url(url)
else:
pass
def parse(self, response):
pic_item = PicItem()
img_nodes = response.css('div.topic-list')
pic_item['href'] = img_nodes.css('a::attr(href)').extract()
pic_item['src'] = img_nodes.css('img::attr(src)').extract()
pic_item['title'] = img_nodes.css('span::text').extract()
yield pic_item
def parse(self, response):
# if the image address start with http://www.xiaohuar.com/list-，I will get it's name and address
if response.url.startswith("http://www.xiaohuar.com/list-"):
allPics = response.xpath('//div[@class="img"]/a')
for pic in allPics:
# Process each image separately, take out its' name and address.
item = PicItem()
name = pic.xpath('./img/@alt').extract()[0]
addr = pic.xpath('./img/@src').extract()[0]
addr = 'http://www.xiaohuar.com'+addr
item['name'] = name
item['addr'] = addr
# Return crawled data
yield item
# get all the address links
urls = response.xpath("//a/@href").extract()
for url in urls:
# if address start with http://www.xiaohuar.com/list-，and not in the collection, get the message
if url.startswith("http://www.xiaohuar.com/list-"):
if url in XhSpider.url_set:
pass
else:
XhSpider.url_set.add(url)
# the default callback function is parse, you can assign it
# by 'from scrapy.http import Request'
# from scrapy.http import Request
# Request(url,callback=self.parse)
yield self.make_requests_from_url(url)
else:
pass
def parse(self, response):
allpics = response.xpath('//div[@class="img"]/a')
for pic in allpics:
item = PicItem()
name = pic.xpath('./img/@alt').extract()[0]
addr = pic.xpath('./img/@src').extract()[0]
if 'http' in addr:
addr = addr
else:
addr = 'http://www.xiaohuar.com' + addr
item['name'] = name
item['addr'] = addr
yield item
# 获取所有的地址链接
urls = response.xpath('//a/@href').extract()
for url in urls:
if url.startswith('http://www.xiaohuar.com/list-'):
if url in XhSpider.url_set:
pass
else:
XhSpider.url_set.add(url)
yield self.make_requests_from_url(url)
else:
pass
def parse_detail(self, response):
urls = response.xpath(
'//div[@class="entry-content"]/p/img/@src').extract()
for url in urls:
url = [url]
print(url)
it1 = PicItem()
it1['image_urls'] = url
yield it1
def parse(self, response):
allPics = response.xpath("//div[@class='img']/a")
for pic in allPics:
item = PicItem()
name = pic.xpath("./img/@alt").extract()[0]
addr = pic.xpath("./img/@src").extract()[0]
addr = "http://www.xiaohuar.com" + addr
item["name"] = name
item["addr"] = addr
yield item
def parse(self, response):
s_re = re.compile(r'img class="lazy" src="(.*?)"')
se = re.findall(s_re, response.text)
item = PicItem()
srcs = []
for i in se:
#item['title'] = i[0]
srcs.append(i)
item['src'] = se
yield item
def parse(self, response):
# 获取所有图片的a标签
allPics = response.xpath(' //*[@id="imgid"]/a')
for pic in allPics:
# 分别处理每个图片，取出名称及地址
item = PicItem()
addr = pic.xpath('./imgid/@href').extract()[0]
addr = 'http://image.baidu.com' + addr
item['addr'] = addr
# 返回爬取到的数据
yield item
def parse(self, response):
# 获取所有图片的a标签
allPics = response.xpath('//td[@class="wordbook-wordlist-name"]/a')
for pic in allPics:
# 分别处理每个图片，取出名称及地址
item = PicItem()
#name = pic.xpath('./img/@alt').extract()[0]
addr = pic.xpath('./@href').extract()[0]
addr = 'http://www.xiaohuar.com' + addr
#item['name'] = name
item['addr'] = addr
# 返回爬取到的数据
yield item
def parse(self, response):
# 获取所有图像的a标签
allPics = response.xpath('//div[@class="img"]/a')
for pic in allPics:
# 分别处理每个图片取出名称及地址
item = PicItem()
name = pic.xpath('./img/@alt').extract()[0]
addr = pic.xpath('./img/@src').extract()[0]
addr = 'http://www.xiaohuar.com' + addr
item['name'] = name
item['addr'] = addr
# 返回爬取数据
yield item
def parse(self, response):
into = response.xpath(
'//div[@class = "post-module-thumb"]/a/@href').extract()
for u in into:
item1 = PicItem()
item1['detailed'] = u
yield scrapy.Request(
item1['detailed'],
callback=self.parse_detail,
)
ifnxt = response.xpath('//div[@class="btn-pager"]').extract()[0]
if "empty button" in ifnxt:
nxt = response.xpath(
'//div[@class="btn-pager"]/a/@href').extract()[0]
yield scrapy.Request(nxt, callback=self.parse)
def parse(self, response):
print("status:"+str(response.status))
pics = response.xpath('//img[@class="img-fluid"]')
#print("movies:"+str(movies))
#print(pics)
for pic in pics:
item = PicItem()
src = pic.xpath('./@src').extract()
name = pic.xpath('./@alt').extract()
if len(name) != 0:
item['name'] = name[0]
#print(name)
#print(src[0])
#item['name'] = name[0]
item['src'] = src[0]
yield item
def parse(self, response):
item = PicItem()
imgurls = response.css(".post img::attr(src)").extract()
item['imgurl'] = imgurls
yield item
pass
def parse(self, response):
if (False == XhSpider.url_list_db.query(response.url, 1)):
XhSpider.url_list_db.update(response.url)
#print ("2.get img ing ...... ",sys._getframe().f_lineno)
if response.url.startswith("https://www.zbjuran.com/mei/"):
allPics = response.xpath('//center/div[@class="picbox"]')
#print ("2.get img ing ...... ",sys._getframe().f_lineno )
for pic in allPics:
# 分别处理每个图片，取出名称及地址
#print ("2.get img ing ...... ",sys._getframe().f_lineno )
item = PicItem()
#print ("2.get img ing ...... ",sys._getframe().f_lineno )
addr = ""
if len(pic.xpath('./img/@src')) >= 1:
addr = pic.xpath('./img/@src').extract()[0]
else:
addr = pic.xpath('./p/img/@src').extract()[0]
#print ("2.get img ing ...... ",sys._getframe().f_lineno )
name_1 = response.xpath(
'//div[@class="title"]/h2/text()').extract()[0]
#print ("2.get img ing ...... ",sys._getframe().f_lineno )
#print (name_1)
name_2 = addr.replace('/', '_').replace(':', '_')
name = ""
name_obj = pic.xpath('./img/@alt')
if len(name_obj) >= 1:
name = name_obj.extract()[0]
if len(name_1) >= 1:
item['name'] = name_1
else:
if len(name) >= 1:
item['name'] = name
else:
item['name'] = name_2
if addr.startswith('/'):
addr = "https://www.zbjuran.com/" + addr
item['addr'] = addr
# 返回爬取到的信息
#print ("hav:",item['addr'],item['name'])
#print ("2.get img ing ...... ",sys._getframe().f_lineno )
yield item
print("2.get img ing ...... ", sys._getframe().f_lineno)
# 获取所有的地址链接
#print ("2.get href ing ...... ")
urls = response.xpath("//a/@href").extract()
for url in urls:
#print(url)
url_arr = url.split("_")
# 如果地址以http://www.xiaohuar.com/list-开头且不在集合中，则获取其信息
if url.startswith("/mei/") and url.endswith(".html"):
url_whole = "https://www.zbjuran.com" + url
if XhSpider.url_list_db.query(url_whole):
#print ("Exist:",url,url_whole)
pass
else:
#XhSpider.url_set.add(url_whole)
XhSpider.url_list_db.insert(url_whole)
# 回调函数默认为parse,也可以通过from scrapy.http import Request来指定回调函数
# from scrapy.http import Request
# Request(url,callback=self.parse)
print("add", url_whole)
yield self.make_requests_from_url(url_whole)
elif url_arr[0].isdigit():
u_arr = response.url.split("/")
u_arr.pop()
u_arr.append(url)
url_whole = "/"
url_whole = url_whole.join(u_arr)
if XhSpider.url_list_db.query(url_whole):
#print ("Exist:",url,url_whole)
pass
else:
print("add", url_whole)
#XhSpider.url_set.add(url_whole)
XhSpider.url_list_db.insert(url_whole)
# 回调函数默认为parse,也可以通过from scrapy.http import Request来指定回调函数
# from scrapy.http import Request
# Request(url,callback=self.parse)
yield self.make_requests_from_url(url_whole)
elif url.startswith("http") and url.endswith(".html"):
url_whole = url
if XhSpider.url_list_db.query(url_whole):
#print ("Exist:",url,url_whole)
pass
else:
#XhSpider.url_set.add(url_whole)
XhSpider.url_list_db.insert(url_whole)
# 回调函数默认为parse,也可以通过from scrapy.http import Request来指定回调函数
# from scrapy.http import Request
# Request(url,callback=self.parse)
print("add", url_whole)
yield self.make_requests_from_url(url_whole)
else:
pass
print("3.get waiting href ... ")
url_whole = XhSpider.url_list_db.query_data()
if len(url_whole) > 10:
yield self.make_requests_from_url(url_whole)
else:
print("4. we finished this site")
def parse_url(self, response):
items = PicItem()
pic_list = response.xpath("//img/@src").extract()
for pic in pic_list:
items['pic_url'] = pic
yield items
