def parse_content(self, response):
category = response.meta['category']
img_urls = response.xpath('//img[@class="screen"]/@src').extract()
item = ImgsItem()
item["category"] = category
item["image_urls"] = ["http://www.goodwp.com/" + img_urls[0]]
yield item
def parse_content(self, response):
category = response.meta['category']
img_urls = response.xpath('//a[@class="img"]/img/@src').extract()
item = ImgsItem()
item["category"] = category
item["image_urls"] = ["https://bonpic.com" + img_urls[0]]
yield item
def parse_content(self, response):
category=response.meta['category']
img_urls = response.xpath('//div[@class="png_big"]/a/img/@src').extract()
item = ImgsItem()
item["category"] = category
item["image_urls"] = ["http://pngimg.com"+img_urls[0]]
yield item
def parse(self, response):
content = response.text
pattern_url = re.compile(
r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+'
)
links = re.findall(pattern_url, content)
keyword = [
"p=tbn", "images", "image", "jpg", "png", "jpeg", "PNG", "JPG",
"JPEG"
]
img_urls = []
for link in links:
url = link.encode("utf8").decode('unicode_escape')
is_img = any([word in url for word in keyword])
if is_img:
img_urls.append(url)
item = ImgsItem()
item["category"] = self.category
item["image_urls"] = img_urls
yield item
if links:
current_num = re.findall('&ijn=(.*?)&start=', response.url)[0]
url = 'https://www.google.com/search?ei=aM0JXfmZBcqD8gXIy7ww&yv=3&q={category}&tbm=isch&vet=10ahUKEwj57YWU7fTiAhXKgbwKHcglDwYQuT0ITCgB.aM0JXfmZBcqD8gXIy7ww.i&ved=0ahUKEwj57YWU7fTiAhXKgbwKHcglDwYQuT0ITCgB&ijn={page}&start={page}00&asearch=ichunk&async=_id:rg_s,_pms:s,_fmt:pc'.format(
category=quote(self.category), page=int(current_num) + 1)
yield scrapy.Request(url=url,
callback=self.parse,
dont_filter=True)
def parse_content(self, response):
category=response.meta['category']
img_urls = response.xpath('//*[@id="photoImage"]/@src').extract()
item = ImgsItem()
item["category"] = category
item["image_urls"] = img_urls
yield item
def parse_content(self, response):
img_urls = response.xpath('//img[@id="mainImg"]/@src').extract()
img_url="http:"+img_urls[0]
item = ImgsItem()
item["image_urls"] = [img_url]
item["category"] = self.category
yield item
def parse_content(self, response):
img_urls = response.xpath(
'//ul[@class="p-slider__nav"]/li/img/@src').extract()
item = ImgsItem()
item["image_urls"] = ["https://ec.shop.acure-fun.net" + img_urls[0]]
item["category"] = "image_acure"
yield item
def parse_item(self, response):
img_urls = response.xpath(
'//*[@id="post_content"]//img/@src').extract()
for img_url in img_urls:
item = ImgsItem()
item['url'] = img_url
yield item
def parse_content(self, response):
img_urls = response.xpath(
'//div[@class="productWrap"]/p/img/@src').extract()
item = ImgsItem()
item["image_urls"] = ["https://www.ajinomoto.co.jp/" + img_urls[0]]
item["category"] = "image_ajinomoto"
yield item
def parse_content(self, response):
img_urls = response.xpath(
'//a[@class="product-info-zoom"]/img/@src').extract()
item = ImgsItem()
item["image_urls"] = img_urls
item["category"] = "image_japantrendshop"
yield item
def parse_content(self, response):
img_urls = response.xpath(
'//div[@id="featured-img-id"]/img/@src').extract()
item = ImgsItem()
item["category"] = self.category
item["image_urls"] = img_urls
yield item
def parse(self, response):
resp = response.text
html = etree.HTML(resp)
img_urls = html.xpath('//img[@itemprop="thumbnail"]/@src')
item = ImgsItem()
item["category"] = self.category
item["image_urls"] = img_urls
yield item
def parse_content(self, response):
category=response.meta['category']
img_urls = response.xpath('//div/p//img/@src').extract()
print(img_urls)
item = ImgsItem()
item["category"] = category
item["image_urls"] = img_urls
yield item
def parse_content(self, response):
img_urls = response.xpath(
'//img[@class="attachment-post-thumbnail size-post-thumbnail wp-post-image"]/@src'
).extract()
item = ImgsItem()
item["image_urls"] = img_urls
item["category"] = "image_asahiya"
yield item
def parse(self, response):
img_urls = response.xpath('//p[@class="imgPart"]/img/@src').extract()
for img_url in img_urls:
img_url = "https://www.kagome.co.jp" + img_url
item = ImgsItem()
item["image_urls"] = [img_url]
item["category"] = "image_kagome"
yield item
def parse_content(self, response):
pattern = response.meta['pattern']
img_urls = response.xpath(
'//a[@id="detailsGallery_opener"]/img/@data-zoom-image').extract()
item = ImgsItem()
item["image_urls"] = img_urls
item["category"] = pattern[0]
yield item
def parse(self, response):
page = response.text
pattern = re.findall(
r"data-photo-modal-image-download-link=\\'(https://images.pexels.com/photos/.*?\.jpg&fm=jpg)\\",
page)
item = ImgsItem()
item["category"] = self.category
item["image_urls"] = pattern
yield item
def parse_url(self, response):
resp = response.text
reg = r'src="(https://timgsa.baidu.com/timg.*?g.*?)"'
imgre = re.compile(reg)
img_list = re.findall(imgre, resp)
item = ImgsItem()
item["category"] = self.category
item["image_urls"] = img_list
yield item
def parse_content(self, response):
img_urls = response.xpath(
'//a[@class="modal-open"]/span/img/@src').extract()
category = response.xpath(
'//*[@id="breadclumb"]/ol/li[2]/a//text()').extract()
item = ImgsItem()
item["image_urls"] = ["https://www.cecile.co.jp" + img_urls[0]]
item["category"] = category[0] + 'image_cecile'
yield item
def parse_content(self, response):
resp = demjson.decode(response.text)
data = resp.get("results", [])
for img in data:
img = img.get("image_url")
item = ImgsItem()
item["category"] = "image_takeya"
item["image_urls"] = [img]
yield item
def parse(self, response):
page = response.text
json_contents = demjson.decode(page)
for json_content in json_contents["collection"]:
image = json_content["thumbnail"]
item = ImgsItem()
item["category"] = self.category
item["image_urls"] = [image]
yield item
def parse(self, response):
resp = demjson.decode(response.text)
data = resp.get("list", [])
for img in data:
img = img.get("img")
item = ImgsItem()
item["category"] = self.category
item["image_urls"] = [img]
yield item
def parse(self, response):
# resp = json.loads(response.text,strict=False)
resp = demjson.decode(response.text)
data = resp.get("items", [])
for img in data:
pic_url = img.get("pic_url")
item = ImgsItem()
item["category"] = self.category
item["image_urls"] = [pic_url]
yield item
def parse(self, response):
category=response.meta['category']
resp = demjson.decode(response.text)
data = resp.get("items", [])
for img in data:
pic_url = img.get("pic_url")
item = ImgsItem()
item["category"] = category
item["image_urls"] = [pic_url]
yield item
def parse(self, response):
page = response.text
json_contents = demjson.decode(page)
for json_content in json_contents["results"]:
urls = json_content["urls"]
image = urls["raw"]
item = ImgsItem()
item["category"] = self.category
item["image_urls"] = [image]
yield item
def parse_url(self, response):
img_patterns = response.xpath(
'//li[@class="row"]/p/a[1]/@href').extract()
for img_pattern in img_patterns:
pattern = re.findall("\d\/(.*?)\.html", img_pattern)
img_url = "https://catalog-p.meiji.co.jp/imageDisp.php?type=product&id={}".format(
pattern[0])
item = ImgsItem()
item["image_urls"] = [img_url]
item["category"] = "image_meiji"
yield item
def parse_content(self, response):
img_urls = response.xpath(
'//div[@class="img-package"]/img/@src').extract()
item = ImgsItem()
res_url = response.url
pattern = re.findall(r"0\d\/(.*\.html)", res_url)
url = res_url.replace(pattern[0], img_urls[0])
print(url)
item["image_urls"] = [url]
item["category"] = "image_yamazakipan"
yield item
def parse_content(self, response):
category = response.xpath('//*[@id="contents"]/div[1]/div/ol/li[2]/a/text()').extract()
img_urls = response.xpath('//img[@class="BigImage "]/@src').extract()
item = ImgsItem()
item["image_urls"] = ["http:"+img_urls[0]]
category = category[0]
if "/" in category:
category=re.sub("/","",category)
item["category"] = category+'image_dccoffee'
else:
item["category"] = category+'image_dccoffee'
yield item
def parse_content(self, response):
category = response.meta['category']
img_urls = response.xpath('//img[@class="BigImage "]/@src').extract()
item = ImgsItem()
item["image_urls"] = ["http:"+img_urls[0]]
category = category[0]
if "/" in category:
category=re.sub("/","",category)
item["category"] = category+"image_coffeefriend"
else:
item["category"] = category+"image_coffeefriend"
yield item
def parse(self, response):
category = response.meta['category']
page = response.text
json_contents = demjson.decode(page)
for json_content in json_contents["data"]:
url = json_content["url"]
image = url["baseUrl"]
image_url = image + "!p4"
item = ImgsItem()
item["category"] = category
item["image_urls"] = [image_url]
yield item
