def get_image_url(self,response):
item = MzituItem()
item['name'] = response.meta['name']
image_urls = response.xpath('//div[@class="main-image"]/p/a/img/@src').extract()
for image_url in image_urls:
item['image_url'] = image_url
yield item
def parse(self, response):
print("================================================")
for _li in response.xpath("//*[@id=\"pins\"]/li"):
item = MzituItem()
_link = _li.xpath("a/@href").extract()[0]
_thumb = _li.xpath("a/img/@data-original").extract()[0]
_title = _li.xpath("span/a/text()").extract()[0]
_time = _li.xpath("span/text()").extract()[0]
item['title'] = re.sub(r'[？\\*|“<>:/]', '', _title)
item['thumb'] = _thumb
item['time'] = _time
item['link'] = _link
print('~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n')
print(_link)
yield item
yield scrapy.Request(_link,
meta={'item': item},
callback=self.parseContent,
headers=self.headers)
print("================================================")
def parsePage(self, response):
try:
img_srcs = []
img_data = MzituItem()
title = response.xpath(
'//h2[@class="main-title"]/text()').extract_first()
img_src = response.xpath(
'//div[@class="main-image"]/p/a/img/@src').extract_first()
total = response.xpath(
'//div[contains(@class,"pagenavi")]/a[last()-1]/span/text()'
).extract_first()
str1 = img_src.rsplit('0', 1)[0]
for i in range(1, int(total) + 1):
if i < 10:
i = '0' + str(i) + '.jpg'
next_img = str1 + i
else:
next_img = str1 + str(i) + '.jpg'
img_srcs.append(next_img)
img_data['title'] = title
img_data['img_list'] = img_srcs
yield img_data
except Exception as e:
print(e)
def pic_download_next(self, response):
item = MzituItem()
pic_name = scrapy.Selector(response).xpath(
'//div[@class="main-image"]/p/a/img/@alt').extract()[0]
# 同上
trantab = str.maketrans('\/:*?"<>|', 'abcdefghi')
item['pic_name'] = pic_name.translate(trantab)
item['pic_url'] = scrapy.Selector(response).xpath(
'//div[@class="main-image"]/p/a/img/@src').extract()[0]
# 进入管道处理
yield item
def parse_item(self, response):
header = {
"User-agent":
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.186 Safari/537.36"
}
item = MzituItem()
item["name"] = response.css(".main-title::text").extract()
item["url"] = response.url
item['image_urls'] = response.css(
".main-image img::attr(src)").extract()
time.sleep(random.randint(3, 6))
yield Request(response.url, headers=header)
yield item
def tuji_parse(self,response):
item=MzituItem()
ref=response.meta['ref']
tuji_url=response.meta['tuji_url']
tuji_page_num=response.xpath('/html/body/div[2]/div[1]/div[4]/a[5]/span/text()').extract_first()
for i in range(int(tuji_page_num)):
if i+1==1:
url=tuji_url
else:
url=tuji_url+'/%s'%(i+1)
item['img_referer']=url
# print('图集第%s页 -url--'%i,url)
yield scrapy.Request(url=url,headers={'referer':ref},callback=self.img_parse,meta={'item':item})
def parse_xijie(self, response):
sel = Selector(response)
item = MzituItem()
rawdate1 = sel.xpath('//div[@class="month_Year"]/text()').extract()[0]
rawdate2 = sel.xpath('//div[@class="day"]/text()').extract()[0]
date = rawdate1[-4:] + '-' + rawdate1[:2] + '-' + rawdate2
title = sel.xpath('//div[@class="metaRight"]/h2/a/text()').extract()[0]
for_pic = sel.xpath('//div[@id="picture"]//img')
for yige in for_pic:
item['date'] = date
item['title'] = title
item['image_urls'] = [yige.xpath('./@src').extract()[0]]
yield item
def get_img_url(self, response):
'''
从page_url的response里
找到图片的下载连接
'''
item = MzituItem()
item['name'] = response.meta['name']
# 找到图片的下载地址，注意有可能一页有两张图
pic = response.xpath('//div[@class="main-image"]//img/@src').extract()
for url in pic:
item['img_urls'] = url
yield item
def parse_item(self, response):
item = MzituItem()
# max_num为页面最后一张图片的位置
max_num = response.xpath(
'//div[@class="pagenavi"]/a[last()-1]/span/text()').extract_first(
default="N/A")
item['name'] = response.xpath(
'//div[@class="content"]/h2/text()').extract_first(default="N/A")
item['url'] = response.url
for num in range(1, int(max_num)):
# page_url 为每张图片所在的页面地址
page_url = response.url + '/' + str(num)
yield scrapy.Request(page_url, callback=self.img_url)
item['image_urls'] = self.img_urls
yield item
def parse_item(self, response):
# sel = Selector(response)
#
# name = sel.xpath("//div[@class='main-image']/p/a/img/@alt").extract()[0]
# print(name)
l = ItemLoader(item=MzituItem(), response=response)
l.add_xpath('image_urls', "//div[@class='main-image']/p/a/img/@src",
Identity())
l.add_xpath('name', "//div[@class='main-image']/p/a/img/@alt",
Identity())
# l.add_value('name', name)
return l.load_item()
def img_url(
self,
response,
):
item = MzituItem()
item['name'] = self.page_name
item['url'] = self.page_url
item['image_urls'] = self.image_urls
img_urls = response.xpath(
"descendant::div[@class='main-image']/descendant::img/@src"
).extract()
for img_url in img_urls:
item['image_urls'].append(img_url)
yield item
def parse(self, response):
item = MzituItem()
#item['title'] = response.xpath('//h2[@class="main-title"]/text()')[0] .extract()
item['title'] = response.xpath(
'//h2[@class="main-title"]/text()')[0].extract().split('（')[0]
item['img'] = response.xpath(
'//div[@class="main-image"]/p/a/img/@src')[0].extract()
item['name'] = response.xpath('//div[@class="main-image"]/p/a/img/@src'
)[0].extract().split('/')[-1]
yield item
next_url = response.xpath(
'//div[@class="pagenavi"]/a/@href')[-1].extract()
if next_url is not None:
yield scrapy.Request(next_url, callback=self.parse)
def get_parse(self, response):
# print(response.request.headers['User-Agent'])
item = MzituItem()
item['title'] = response.xpath(
'//div[@class="main-image"]//img/@alt').extract()[0]
item['imgurl'] = response.xpath(
'//div[@class="main-image"]//img/@src').extract()
yield item
# print(item)
next_page = response.xpath(
"//a/span[contains(text(),'下一页»')]/../@href") #.. ：当前节点父节点
if next_page:
url = next_page[0].extract()
yield scrapy.Request(url, callback=self.get_parse)
def second_handler(self, response):
# 二级页面
item = MzituItem()
# 获取页数链接进行访问
offset = int(
response.xpath('//div[@class="pagenavi"]/a/span/text()')
[4].extract())
# 生成链接访问 遍历链接访问
for i in [
response.url + "/{}".format(str(x))
for x in range(1, offset + 1)
]:
item['Referer'] = i
# 将meta传入链接 访问三级页面
yield scrapy.Request(url=i,
meta={'meta_1': item},
callback=self.parse_ponse)
def parse_get_image(self,response):
#print('11111111111111111111111111111111'+response.url)
item_detail = response.meta["item"]
current = int(response.meta["current"])
imageurl = response.xpath('//div[@class="main-image"]/p/a/img/@src').extract()[0]
#print('22222222222222222222222222222222' + imageurl)
item = MzituItem()
item["mzi_name"] = item_detail["mzi_name"]
item["mzi_link"] = item_detail["mzi_link"]
item["mzi_time"] = item_detail["mzi_time"]
item["mzi_view"] = item_detail["mzi_view"]
item["mzi_image"] = imageurl
if current == 1:
item['mzi_index'] = 0
else:
item['mzi_index'] = current - 1
yield item
def parser_item(self, response):
item = MzituItem()
#得到没套图的名字 extract_first(default=”N/A”)取xpath返回值的第一个元素。如果xpath没有取到值，则返回N/A
#这里我用字符串分割的方法
name = response.selector.xpath(
'/html/body/div[2]/div[1]/div[1]/text()[3]').extract()
item['name'] = name[0][3:-1]
item['url'] = response.url
all_page = response.selector.xpath(
'/html/body/div[2]/div[1]/div[4]/a[5]/span/text()').extract()
for page in range(1, int(all_page[0]) + 1):
#得到每张照片的地址
url = response.url + '/' + str(page)
yield scrapy.Request(url=url, callback=self.img_url)
#上面的循环所有页面执行完 定义的图片url列表也在下面的 img_url函数里添加好了 所以放入容器
item['image_url'] = self.img_urls
yield item
def detail_parse(self, response):
item = MzituItem()
date_str = response.css(
'body > div.main > div.content > div.main-meta > span:nth-child(2)'
).extract_first()
item['month'] = re.search(' (\d{4}-\d{2})-\d{2} ', date_str).group(1)
item['date'] = re.search(' (\d{4}-\d{2}-\d{2}) ', date_str).group(1)
item['title'] = response.css(
'body > div.main > div.content > h2::text').extract_first()
item['url'] = response.url
item['type'] = response.css(
'body > div.main > div.content > div.main-meta > span:nth-child(1) > a::text'
).extract_first()
item['tags'] = ' '.join(
response.css(
'body > div.main > div.content > div.main-tags > a::text').
extract())
return item
def get_img_url(self, response):
'''
从page_url的response里
找到图片的下载链接
:param response:
:return:
'''
item = MzituItem()
item['name'] = response.meta['name']
item['base_urls'] = response.meta['base_urls']
#找到图片的下载地址
pic = response.xpath('//div[@class="main-image"]//img/@src').extract()
for url in pic:
item['img_urls'] = url
yield item
def parse_next(self,response):
node_list = response.xpath('//ul[@id="pins"]/li')
items = []
for node in node_list:
item = MzituItem()
mzi_name = node.xpath('./span[1]/a/text()').extract()[0]
mzi_link = node.xpath('./span[1]/a/@href').extract()[0]
mzi_time = node.xpath('./span[2]/text()').extract()[0]
mzi_view = node.xpath('./span[3]/text()').extract()[0]
item["mzi_name"] = mzi_name
item["mzi_link"] = mzi_link
item["mzi_time"] = mzi_time
item["mzi_view"] = mzi_view
items.append(item)
for item in items:
yield scrapy.Request(item["mzi_link"], meta={"item": item}, callback=self.parse_detail)
def parse_detail(self,response):
item_detail = response.meta["item"]
imageurl = response.xpath('//div[@class="main-image"]/p/a/img/@src').extract()[0]
imagelist = response.xpath('//div[@class="pagenavi"]/a/span/text()').extract()[-2]
url_src = ''
file_name_type = imageurl.split('/')
file_name = file_name_type[len(file_name_type) - 1]
print('%s---------%s',file_name,len(file_name))
if len(file_name) <= 9 and file_name.index('01.jpg') > -1 :
baseURl = imageurl.split('01.jpg')[0]
image_src = ''
item = MzituItem()
for i in range(1, int(imagelist) + 1):
if i == 1:
item["mzi_index"] = 0
else:
item['mzi_index'] = i - 1
if i < 10:
image_src = baseURl + '0' + str(i) + '.jpg'
else:
image_src = baseURl + str(i) + '.jpg'
item["mzi_name"] = item_detail["mzi_name"]
item["mzi_link"] = item_detail["mzi_link"]
item["mzi_time"] = item_detail["mzi_time"]
item["mzi_view"] = item_detail["mzi_view"]
item["mzi_image"] = image_src
yield item
else:
for i in range(1, int(imagelist) + 1):
if i == 1:
url_src = item_detail["mzi_link"]
else:
url_src = '%s/%s' % (item_detail["mzi_link"], str(i))
# print(url_src)
yield scrapy.Request(url_src, meta={"item": item_detail, "current": str(i)},
callback=self.parse_get_image)
def pic_download(self, response):
item = MzituItem()
pic_name = scrapy.Selector(response).xpath(
'//div[@class="main-image"]/p/a/img/@alt').extract()[0]
trantab = str.maketrans('\/:*?"<>|', 'abcdefghi')
# 依然是替换非法字符，之前是为了创建目录，这里是为了把图片应存储的本地分类路劲写入到item中
item['pic_name'] = pic_name.translate(trantab)
# 找到该分类的页数
item['pic_url'] = scrapy.Selector(response).xpath(
'//div[@class="main-image"]/p/a/img/@src').extract()[0]
# 进入管道处理
yield item
# 找到该分类的页数
url_num = scrapy.Selector(response).xpath(
'//div[@class="pagenavi"]/a[last()-1]/span/text()').extract()[0]
# 从第二页开始遍历
for i in range(2, int(url_num) + 1):
link = '{}/{}'.format(response.url, i)
if link not in final_page_link:
# 记录
final_page_link.append(link)
# 调用后续函数，这里不能回调该函数,原因看readme
yield scrapy.Request(link, callback=self.pic_download_next)
def parse_item(self, response):
sel = Selector(response)
item = MzituItem()
item['classification'] = sel.xpath(
'/html/body/div[2]/div[1]/div[1]/a[2]/text()').extract_first(
default="N/A")
item['title'] = sel.xpath('/html/body/div[2]/div[1]/div[1]/text()[3]'
).extract_first(default="N/A")
item['name'] = sel.xpath(
'/html/body/div[2]/div[1]/div[4]/span[1]/text()').extract_first(
default="N/A")
max_num = sel.xpath(
'./*//div[@class="pagenavi"]/a[last()-1]/span/text()'
).extract_first(default="N/A")
print(max_num)
item['url'] = response.url
for num in range(1, int(max_num) + 1):
n_url = response.url + '/' + str(num)
print('pic-' + n_url)
yield scrapy.Request(n_url, callback=self.imgurl)
item['image_urls'] = self.urls
print('ij')
yield item
