def parse(self, response):
hxs = HtmlXPathSelector(response)
videoNameVec = hxs.select('//div/div/div/div/h1/a/text()').extract()
videoViewNumVec = hxs.select('//ul[@class = "info"]/li[3]/text()').extract()
videoPubTimeVec = hxs.select('//ul[@class = "info"]/li[2]/text()').extract()
videoLengthVec = hxs.select('//ul[@class = "info"]/li[1]/text()').extract()
# check for errors
numVN = len(videoNameVec)
numVNV = len(videoViewNumVec)
numPTV = len(videoViewNumVec)
numLV = len(videoLengthVec)
if (numVN != numVNV) or (numVN != numPTV) or (numVN != numLV):
raise NameError( 'fetch failed for tudou' )
# if pass the test, continue to assign to structure
itemList = []
for iVideo in range(numVN):
item = videoItem()
item['name'] = videoNameVec[iVideo]
item['viewNum'] = videoViewNumVec[iVideo]
item['pubTime'] = videoPubTimeVec[iVideo]
item['length'] = videoLengthVec[iVideo]
itemList.append(item)
return itemList
def parse(self, response):
hxs = HtmlXPathSelector(response)
videoNameVec = hxs.select('//div/div/div/div/h1/a/text()').extract()
videoViewNumVec = hxs.select(
'//ul[@class = "info"]/li[3]/text()').extract()
videoPubTimeVec = hxs.select(
'//ul[@class = "info"]/li[2]/text()').extract()
videoLengthVec = hxs.select(
'//ul[@class = "info"]/li[1]/text()').extract()
# check for errors
numVN = len(videoNameVec)
numVNV = len(videoViewNumVec)
numPTV = len(videoViewNumVec)
numLV = len(videoLengthVec)
if (numVN != numVNV) or (numVN != numPTV) or (numVN != numLV):
raise NameError('fetch failed for tudou')
# if pass the test, continue to assign to structure
itemList = []
for iVideo in range(numVN):
item = videoItem()
item['name'] = videoNameVec[iVideo]
item['viewNum'] = videoViewNumVec[iVideo]
item['pubTime'] = videoPubTimeVec[iVideo]
item['length'] = videoLengthVec[iVideo]
itemList.append(item)
return itemList
def parse(self, response):
#inspect_response(response)
hxs = HtmlXPathSelector(response)
videoNameVec = hxs.select('//div[2]/div/div[2]/div/ul/li/a/text()').extract()
videoViewNumVec = hxs.select('//ul/li/span[2]/text()').extract()
videoPubTimeVec = hxs.select('//div[2]/div/ul/li[@class = "v_pub"]/span/text()').extract()
# The format is 20941 characters from the CJK Unified Ideographs block.
# Check if the length is the same
numVN = len(videoNameVec)
numVNV = len(videoViewNumVec)
numPTV = len(videoViewNumVec)
if (numVN != numVNV) or (numVN != numPTV):
raise NameError( 'fetch failed for youku' )
# if pass the test, continue to assign to structure
itemList = []
for iVideo in range(numVN):
item = videoItem()
item['name'] = videoNameVec[iVideo]
item['viewNum'] = videoViewNumVec[iVideo]
item['pubTime'] = videoPubTimeVec[iVideo]
itemList.append(item)
return itemList
def parse(self, response):
#inspect_response(response)
hxs = HtmlXPathSelector(response)
videoNameVec = hxs.select(
'//div[2]/div/div[2]/div/ul/li/a/text()').extract()
videoViewNumVec = hxs.select('//ul/li/span[2]/text()').extract()
videoPubTimeVec = hxs.select(
'//div[2]/div/ul/li[@class = "v_pub"]/span/text()').extract()
# The format is 20941 characters from the CJK Unified Ideographs block.
# Check if the length is the same
numVN = len(videoNameVec)
numVNV = len(videoViewNumVec)
numPTV = len(videoViewNumVec)
if (numVN != numVNV) or (numVN != numPTV):
raise NameError('fetch failed for youku')
# if pass the test, continue to assign to structure
itemList = []
for iVideo in range(numVN):
item = videoItem()
item['name'] = videoNameVec[iVideo]
item['viewNum'] = videoViewNumVec[iVideo]
item['pubTime'] = videoPubTimeVec[iVideo]
itemList.append(item)
return itemList