def parse(driver, url):
products = []
driver.get(url)
elements = util.find_elements_by_css_selector(driver, 'a.product-item')
if not elements: # http://www.louisvuitton.cn/zhs-cn/women/ready-to-wear/furs/_/N-f8lvb3
elements = util.find_elements_by_css_selector(
driver, 'li.listing > a.product-img')
for element in elements:
products.append(element.get_attribute('href').strip())
return ';'.join(products)
def parse(driver, url):
products = []
driver.get(url)
elements = util.find_elements_by_css_selector(driver, 'a.shelf_view-all')
for element in elements:
if element.is_displayed():
driver.execute_script('arguments[0].click();', element)
util.sleep(3)
elements = util.find_elements_by_css_selector(driver, 'li.product > div > a')
for element in elements:
products.append(element.get_attribute('href').strip())
return ';'.join(products)
def parse(driver, url):
products = []
driver.get(url)
elements = util.find_elements_by_css_selector(driver, 'div.product > div > div > a')
if not elements: # http://www.dior.cn/beauty/zh_cn/%E9%A6%99%E6%B0%9B%E4%B8%8E%E7%BE%8E%E5%AE%B9/%E5%BD%A9%E5%A6%86/%E7%9C%BC%E9%83%A8/%E7%9C%BC%E5%BD%B1/fr-eyeshadows-%E7%9C%BC%E5%BD%B1.html
elements = util.find_elements_by_css_selector(driver, 'div.column > div.push-pic > a')
if not elements: # http://www.dior.cn/couture/zh_cn/%E5%A5%B3%E5%A3%AB%E6%97%B6%E8%A3%85/%E5%A4%AA%E9%98%B3%E7%9C%BC%E9%95%9C
elements = util.find_elements_by_css_selector(driver, '[id|=push-produit] > div > div > a')
if not elements: # http://www.dior.cn/couture/zh_cn/%E7%94%B7%E5%A3%AB%E6%97%B6%E8%A3%85/dior-homme-x-sennheiser
elements = util.find_elements_by_css_selector(driver, 'span.univers-part--product > div > div > a')
for element in elements:
products.append(element.get_attribute('href').strip())
return ';'.join(products)
def parse(driver, url):
products = []
driver.get(url)
driver.execute_script('window.scrollBy(0,50000)')
util.sleep(3)
elements = util.find_elements_by_css_selector(
driver, 'section.products > article.item > div > a')
if not elements: # https://www.chloe.cn/cn/chloe/%E5%A5%B3%E5%A3%AB/subhome/accessories_section
elements = util.find_elements_by_css_selector(driver,
'article.product >a')
for element in elements:
products.append(element.get_attribute('href').strip())
return ';'.join(products)
def parse(driver, url):
products = []
driver.get(url)
elements = util.find_elements_by_css_selector(driver,
'h3.fnb_product-title > a')
if not elements: # https://www.chanel.com/zh_CN/watches-jewelry/watches/c/jewelry-watches/W009
elements = util.find_elements_by_css_selector(
driver, 'div.product-item-wrapper > a')
if not elements: # https://www.chanel.cn/zh_CN/fragrance-beauty/skincare/c/le-lift.html
elements = util.find_elements_by_css_selector(
driver, 'figure.fnb_prd-info > a')
for element in elements:
products.append(element.get_attribute('href').strip())
return ';'.join(products)
def parse(driver, url):
products = []
driver.get(url)
elements = util.find_elements_by_css_selector(driver, 'a.prod-link')
if elements:
for element in elements:
if element.get_attribute('style') != 'display: none;':
products.append(element.get_attribute('href').strip())
else: # http://www.cartier.cn/zh-cn/pages/fragrances/les-heures-de-parfum%E7%B3%BB%E5%88%97.html
elements = util.find_elements_by_css_selector(
driver, 'div.comp-rich-text > p > a')
for i in range(len(elements) - 1):
products.append(elements[i].get_attribute('href').strip())
return ';'.join(products)
def parse(driver, url):
products = []
driver.get(url)
elements = util.find_elements_by_css_selector(driver, 'a.item-url.open-productdetail')
for element in elements:
products.append(element.get_attribute('href').strip())
return ';'.join(products)
def parse(driver, url):
products = []
driver.get(url)
elements = util.find_elements_by_css_selector(driver, 'a.item-display-image-container')
for element in elements:
products.append(element.get_attribute('href').strip())
return ';'.join(products)
def parse(driver, url):
products = []
driver.get(url)
elements = util.find_elements_by_css_selector(driver,
'div.product > div > a')
for element in elements:
products.append(element.get_attribute('href').strip())
return ';'.join(products)
def parse(driver, url):
products = []
driver.get(url)
elements = util.find_elements_by_css_selector(
driver, 'article.search-item > header > a')
for element in elements:
products.append(element.get_attribute('href').strip())
return ';'.join(products)
def parse(driver, url):
products = []
driver.get(url)
while True:
elements = util.find_elements_by_css_selector(driver, 'a.bul-btn-more')
cont = False
for element in elements:
if element.is_displayed():
cont = True
driver.execute_script('arguments[0].click();', element)
util.sleep(3)
if not cont:
break
elements = util.find_elements_by_css_selector(driver, 'a.product-link')
for element in elements:
products.append(element.get_attribute('href').strip())
return ';'.join(products)
def parse(driver, url):
products = []
driver.get(url)
elements = util.find_elements_by_css_selector(
driver, 'figure.product-image > a.thumb-link')
for element in elements:
products.append(element.get_attribute('href').strip())
return ';'.join(products)
def get_images(driver):
images = ''
texts = set([])
elements = util.find_elements_by_css_selector(driver, '#ItemSlideshowViewport > div.bx-wrapper > div.bx-viewport > ul > li > img')
for element in elements:
image = ((element.get_attribute('srcset').split(','))[0].split(' '))[0].strip()
texts.add(image)
images = ';'.join(texts)
return images
def parse(driver, url):
products = []
driver.get(url)
driver.execute_script('window.scrollBy(0,50000)')
time.sleep(3)
elements = util.find_elements_by_css_selector(driver, 'a.js-producttile_link')
for element in elements:
products.append(element.get_attribute('href').strip())
return products
def parse(driver, url):
products = []
driver.get(url)
for i in range(10): # 确保页面拉到最下面，所有商品得到展示。
driver.execute_script('window.scrollBy(0, 10000)')
util.sleep(1)
elements = util.find_elements_by_css_selector(driver, 'li.item > div> div.product-image-box >a')
for element in elements:
products.append(element.get_attribute('href').strip())
return ';'.join(products)
def get_intro(driver):
intro = ''
element = util.find_element_by_css_selector(driver, 'div[data-accordionpanel=item_detail] > span.icon-plus')
if element:
element.click()
texts = []
elements = util.find_elements_by_css_selector(driver, 'div.item-description > ul > li > span.value')
for element in elements:
texts.append(element.text.strip())
if texts:
intro = '\n'.join(texts)
return intro
