class Model_Scraper_Keywords_First(Model_Scraper_Standard):
def __init__(self, region):
super(Model_Scraper_Keywords_First, self).__init__(region)
self.region = region
self.processor = Service_Functions().getProcessor(
'Keywords_First', region)
def scraper(self, keywords):
self.process = Model_Scraper_Standard(self.region)
url = "https://www.amazon." + self.region + "/gp/search?keywords=" + keywords + "&page=1"
print(url)
try:
content = self.process.processkeywords(url)
except Exception as err:
print(err)
try:
if (content):
# 这边写解析代码
result = self.processor.process(content)
if (result):
return result
elif (content == None):
return None
else:
return False
except:
return False
class Model_Scraper_Product_Base(Model_Scraper_Standard):
def __init__(self, region):
super(Model_Scraper_Product_Base, self).__init__(region)
self.region = region
self.processor = Service_Functions().getProcessor(
'Product_Base', region)
def scrape(self, asin):
self.process = Model_Scraper_Standard(self.region)
url = "https://www.amazon." + self.region + "/dp/" + asin + "?th=1&psc=1"
print(url)
try:
content = self.process.process(url)
except Exception as err:
print(err)
try:
if (content):
# 解析代码
data = self.processor.process(content.encode('utf-8'))
if (data):
return data
else:
return False
elif (content == None):
return None
else:
return False
except:
return False
class Model_Scraper_TopReviewer(Model_Scraper_Standard):
def __init__(self, region):
self.region = region
self.processor = Service_Functions().getProcessor(
'TopReviewer', region)
def scrape(self, begin, end):
if not str(begin).isdigit() and not str(end).isdigit() and begin > end:
return Model_Static_Scrape_Status.FAILED
self.process = Model_Scraper_Standard(self.region)
data = []
for i in range(begin, end):
pageUrl = "https://www.amazon." + self.region + "/review/top-reviewers?page=" + str(
i)
pageContent = self.process.processTopReviewer(pageUrl)
if not pageContent:
continue
rankEnd = i * 10
rankBegin = rankEnd - 9
pageResult = self.processor.process(pageContent, rankBegin,
rankEnd + 1)
if (pageResult):
# 数组合并
data.append(pageResult)
if (len(data)):
return data
class Model_Scraper_Product_Offer1(Model_Scraper_Standard):
def __init__(self, region):
self.region = region
self.processor = Service_Functions().getProcessor(
'Product_Offer', region)
def process(self, asin):
self.processOffer = Model_Scraper_Standard(self.region)
content = self.processOffer.processOffer(self.region, asin)
if (content):
return content
# def scrapeInventory(self, data):
# if (data == '' or data == None):
# return Model_Static_Scrape_Status.FAILED
# url ="http://www.amazon."+self.region+"/gp/aws/cart/add.html"
# fields = []
# session_id = None
def scrape(self, asin):
content = self.process(asin)
if (content):
# 这边写解析代码, 通过解析返回的数据再进行库存的抓取
print(content)
data = self.processor.process(content.encode('utf-8'))
if (data):
print(data)
# 通过解析得到的数据进行库存的计算
# Inventory = self.scrapeInventory(asin, data)
# print (Inventory)
pageCount = self.processor.getPageCount(content)
# print (pageCount)
if (pageCount > 1):
for i in range(2, int(pageCount) + 1):
# print (i)
index = str((i - 1) * 10)
pageUrl = "http://www.amazon." + "com" + "/gp/offer-listing/" + asin + "/ref=olpOffersSuppressed?ie=UTF8&f_new=true&overridePriceSuppression=1&startIndex=" + index
# print (pageUrl)
pageContent = self.processPageOffer(pageUrl)
if (pageContent):
print(pageContent)
pageResult = self.processor.process(
pageContent.encode('utf-8'))
if (pageResult):
print(pageResult)
class Model_Scraper_Keywords(Model_Scraper_Standard):
def __init__(self, region):
super(Model_Scraper_Keywords, self).__init__(region)
self.region = region
self.processor = Service_Functions().getProcessor('Keywords', region)
def scraper(self, keywords):
self.process = Model_Scraper_Standard(self.region)
url = "https://www.amazon."+self.region+"/gp/search?keywords="+keywords+"&page=1"
# 不显示浏览器
# with Display(backend="xvfb", size=(1440, 900)):
print (url)
try:
content = self.process.processkeywords(url)
except Exception as err:
print (err)
try:
if (content):
# 这边写解析代码
data = []
result = self.processor.process(content.encode('utf-8'), 1)
if (result):
# print (result)
data.append(result)
pagecount = int(self.processor.getPageCount(content))
if (pagecount > 5):
pagecount = 5
# pagecount = 1
if (pagecount > 1):
for i in range(2, pagecount + 1):
pageurl = "https://www.amazon." + self.region + "/gp/search?keywords=" + keywords + "&page=" + str(i)
print (pageurl)
pagecontent = self.process.processkeywords(pageurl)
if (pagecontent):
pageresult = self.processor.process(pagecontent.encode('utf-8'), i)
# print (pageresult)
data.append(pageresult)
return data
elif (content == None):
return None
else:
return False
except:
return False
class Model_Scraper_Sina_Auto():
def __init__(self):
self.processor = Service_Functions().getSinaProcessor('Sina_Base')
def scrape(self, url):
self.process = Model_Scraper_Sina_Standard()
html = self.process.process_auto(url)
if (html):
content = self.processor.process(html)
return (content)
class Model_Scraper_Seller_Product(Model_Scraper_Standard):
def __init__(self, region):
self.region = region
self.processor = Service_Functions().getProcessor(
'Seller_Product', region)
def scrape(self, merchantId):
if not merchantId:
return False
url = "https://www.amazon." + self.region + "/s?merchant=" + merchantId
print(url)
content = Model_Scraper_Standard(self.region).processSellerProduct(url)
if (content):
result = self.processor.process(content)
if (result):
data = []
data.append(result)
pagecount = int(self.processor.getPageCount(content))
pagecount = 1 # 测试
if (pagecount > 1):
if (pagecount > 50):
pagecount = 50 # 测试 原为50
for i in range(2, pagecount + 1):
pageurl = "https://www.amazon." + self.region + "/s?merchant=" + merchantId + "&page=" + str(
i)
print(pageurl)
pageContent = Model_Scraper_Standard(
self.region).processSellerProduct(pageurl)
if not pageContent:
continue
pageResult = self.processor.process(pageContent)
if (pageResult):
data.append(pageResult)
return data
return Model_Static_DownloadQueue_Status().SCRAPED_NO_DATA
return Model_Static_DownloadQueue_Status().FAILED
class Model_Scraper_Sina_Base():
def __init__(self):
self.processor = Service_Functions().getSinaProcessor('Sina_Base')
def scrape(self, url):
self.process = Model_Scraper_Sina_Standard()
html = self.process.process(url)
if (html):
content = self.processor.process(html)
return (content)
def process_content(self, html, url_id, url):
scrape = Model_Processor_Sina_Content()
content = scrape.process(html)
content['url_id'] = url_id
content['url'] = url
return content
class Model_Scraper_Seller_Base(Model_Scraper_Standard):
def __init__(self, region):
self.region = region
self.processor = Service_Functions().getProcessor(
'Seller_Base', region)
def scrape(self, merchantId):
if not merchantId:
return False
url = "http://www.amazon." + self.region + "/gp/aag/main?seller=" + merchantId
content = Model_Scraper_Standard(self.region).processSeller(url)
if (content):
data = self.processor.process(content)
if (data):
return data
return Model_Static_DownloadQueue_Status().SCRAPED_NO_DATA
return Model_Static_DownloadQueue_Status().FAILED
class Model_Scraper_Tencent_Sports():
def __init__(self):
self.processor = Service_Functions().getTencentProcessor(
'Tencent_Sports')
def scrape(self, url):
self.process = Model_Scraper_Tencent_Standard()
html = self.process.process_gb2312(url)
# print (html)
if (html):
content = self.processor.process(html)
return (content)
def process_content(self, html, url_id, url):
scrape = Model_Processor_Tencent_Content()
content = scrape.process(html)
content['url_id'] = url_id
content['url'] = url
return content
class Model_Scraper_Product_Review(Model_Scraper_Standard):
def __init__(self, region):
self.region = region
self.processor = Service_Functions().getProcessor(
'Product_Review', region)
def scrape(self, asin, scrapedCount):
self.process = Model_Scraper_Standard(self.region)
url = "https://www.amazon." + self.region + "/gp/product-reviews/" + asin + "?sortBy=recent&pageNumber=1"
print(url)
content = self.process.processReview(url)
if (content):
data = {}
items = []
summary = self.processor.getSummary(content.encode('utf-8'))
if (summary):
# print (summary)
data['summary'] = summary
# 处理首页数据
result = self.processor.process(content.encode('utf-8'))
if (result):
# print (result)
items.append(result)
newScrapedCount = 10
if (data['summary']['page_count']
and data['summary']['page_count'] > 0):
# print (data['summary']['page_count'])
pageCount = data['summary']['page_count']
# 已经抓取的页面
scrapedPageCount = int(floor(int(scrapedCount) / 10))
# print (scrapedPageCount)
# 实际需要抓取的页面
pageCount = pageCount - scrapedPageCount
# print (pageCount)
if (pageCount > 20):
pageCount = 2
if (pageCount >= 2):
newScrapedCount = pageCount * 10
for i in range(2, pageCount + 1):
pageUrl = "https://www.amazon." + self.region + "/gp/product-reviews/" + asin + "?sortBy=recent&pageNumber=" + str(
i)
print(pageUrl)
pageContent = self.process.processReview(pageUrl)
if not pageContent:
continue
# 处理page数据
pageResult = self.processor.process(
pageContent.encode("utf-8"))
if (pageResult):
# print (pageResult)
# items = []
items.append(pageResult)
# print (items[0])
# print (items[1])
data['list'] = items
if (len(data) > 0):
data['new_scraped_count'] = newScrapedCount
# print (data)
return data
else:
return Model_Static_Scrape_Status.SUCCESS_NO_DATA
elif (content == None):
return None
else:
return False