def parse_element(script):
content = None
content_length = 0
uns = unhexlify(script)
mark = uns[0]
if 0x00 <= mark and mark <= 0x4B:
content_length = mark
content = script[2:2 + content_length * 2]
script = script[2 + content_length * 2:]
elif 0x4C <= mark and mark <= 0x4E:
if 0x4C == mark:
content_length = int(script[2:4], 16)
content = script[4:4 + content_length * 2]
script = script[4 + content_length * 2:]
if 0x4D == mark:
content_length = int(CT.big_or_little(script[2:6]), 16)
content = script[6:6 + content_length * 2]
script = script[6 + content_length * 2:]
if 0x4E == mark:
content_length = int(CT.big_or_little(script[2:10]), 16)
content = script[10:10 + content_length * 2]
script = script[10 + content_length * 2:]
elif 0x4F == mark:
content = -1
script = script[2:]
elif 0x51 <= mark and mark <= 0x60:
content = mark - 0x50
script = script[2:]
else:
pass
return content, script
def solveReviewerBack(self):
# newAsinList = []
with open("../data/" + self.fetchDate.isoformat() + "/reviewer.txt",
"w") as fout:
ct = CommonTool(fout)
ct.writeln(Reviewer.Reviewer.tableHead)
for i, reviewerID in enumerate(self.reviewerList):
if reviewerID == '':
continue
print 'solve reviewer {0} of {1}: {2}'.format(
i, len(self.reviewerList), reviewerID)
reviewer = Reviewer.loadReviewer(reviewerID)
# newAsinList.extend(reviewer.getReviewedBookList())
reviewer.saveProfileUp(ct)
def printReviews(self, ct=None):
fout = ''
flag = False
if ct is None:
flag = 1
if not os.path.exists("../data/" + self.fetchDate.isoformat() +
"/review/"):
os.makedirs(
"../data/" + self.fetchDate.isoformat() + "/review/")
ct = CommonTool()
if not os.path.exists("../data/" + self.fetchDate.isoformat() +
"/review/review.txt"):
fout = open(
"../data/" + self.fetchDate.isoformat() +
"/review/review.txt", "w")
print "writing reviews in new file"
ct.setFout(fout)
ct.writeln(Review.Review.tableHead)
else:
fout = open(
"../data/" + self.fetchDate.isoformat() +
"/review/review.txt", "a")
ct.setFout(fout)
for reviewID in self.reviewList:
print "printing reviews"
review = Review.loadReview(reviewID, self.fetchDate)
review.printData(ct)
review.insertReviewDataIntoTable()
if flag:
fout.close()
def solveRightCol(self):
try:
divRightCol = self.html.xpath(".//div[@id='rightCol']")[0]
divBuyBoxInner = divRightCol.xpath(".//div[@id='buyBoxInner']")[0]
priceSpan = divBuyBoxInner.xpath("./div/div[2]/ul/li/span")
if len(priceSpan) == 0:
self.listPrice = 0
else:
priceType = priceSpan[0].xpath("./span")[0].text.strip()
priceValue = priceSpan[0].xpath("./span")[1].text.strip()
if priceType == 'List Price:':
self.listPrice = CommonTool.strToFloat(priceValue)
else:
self.listPrice = 0
del priceType
del priceValue
del priceSpan
del divBuyBoxInner
del divRightCol
except Exception, e:
print 'RightCol error: %s' % str(e)
self.listPrice = 0
def getProductLinksUsingThreads(self,productList):
print "getting products using thread method"
for link in productList:
linkPage = MyHtml.getHtml(
link, self.rID + "_AllProductLinks_" + str(self.page))
trObjs = linkPage.xpath(
".//body/table[2]/tr[1]/td[2]/table[2]/tr[@valign='top']")
if link is self.firstLink:
try:
firstTimeObj = trObjs[-1]
except LookupError:
print link
exit(0)
fTime = firstTimeObj.xpath("./following-sibling::*")
if len(fTime) == 0:
self.fRevTime = 'N/A'
else:
# print etree.tostring(fTime[0])
fTime = fTime[0].xpath(".//nobr")
if len(fTime) == 0:
self.fRevTime = 'N/A'
else:
self.fRevTime = fTime[0].text.strip()
self.fRevTime = CommonTool.strToDate(self.fRevTime)
del fTime
if link is self.lastLink:
lastTimeObj = trObjs[0]
lTime = lastTimeObj.xpath("./following-sibling::*")
if len(lTime) == 0:
self.lRevTime = 'N/A'
else:
# print etree.tostring(lTime[0])
lTime = lTime[0].xpath(".//nobr")
if len(lTime) == 0:
self.lRevTime = 'N/A'
else:
self.lRevTime = lTime[0].text.strip()
self.lRevTime = CommonTool.strToDate(self.lRevTime)
del lTime
for trObj in trObjs:
tableObj = trObj.xpath(
"./td[@class='small'][3]/table[@class='small']")
# aLink
if len(tableObj) != 0:
aLink = tableObj[0].xpath(".//a")
if len(aLink) == 0:
aLink = ''
else:
aLink = aLink[0].attrib['href']
# rate
rateObj = trObj.xpath("./following-sibling::*")
rate = 'N/A'
if len(rateObj) != 0:
try:
rateObj1 = rateObj[0].xpath(".//img")
title = rateObj1[0].attrib['title']
rate = title.split("out")[0].strip()
self.sum = self.sum + float(rate)
self.counter = self.counter + 1
except Exception, e:
sys.stderr.write(str(e) + ' rate Exception\n')
# reviewID
reviewID = ''
rIDObj = rateObj[0].xpath(".//a")
if len(rIDObj) != 0:
reviewID = rIDObj[0].attrib['name']
# label The review is from
label = ''
labelObj = rateObj[0].xpath(".//div[@class='tiny']")
if len(labelObj) != 0:
# verified purchase + the review is from
aObj = labelObj[-1].xpath(".//a")
if len(aObj) != 0:
label = filtTag.filter_tags(
etree.tostring(aObj[0]).strip())
# 1---book 0---product
parLeft = label.find('(')
parRight = label.find(')')
if parLeft == -1 and parRight == -1:
label = '0'
elif label[-1] == ')':
label = label.split('(')
label = label[-1][:-1]
if (label.find('Paperback') != -1) or (label.find('Hardcover') != -1):
label = '1'
bookID = aLink.replace('/ref=cm_cr-mr-title', '')
bookID = bookID[-10:]
self.reviewedBookList.append(bookID)
productList = []
productList.append(aLink)
productList.append(rate)
productList.append(reviewID)
productList.append(label)
self.allProductLinks.append(productList)
del productList
self.page = self.page + 1
async def crawl(self):
self.start = await self.get_state()
self.start += 1
while True:
current_height = await self.get_block_count()
time_a = CT.now()
if self.start < current_height:
stop = self.start + self.max_tasks
if stop >= current_height:
stop = current_height
self.processing.extend([i for i in range(self.start, stop)])
max_height = max(self.processing)
min_height = self.processing[0]
await asyncio.wait(
[self.cache_block(h) for h in self.processing])
if self.processing != sorted(self.cache.keys()):
msg = 'cache != processing'
logger.error(msg)
raise Exception(msg)
sys.exit(1)
await self.update_sys_fee(min_height)
vins = []
vouts = []
claims = []
for block in self.cache.values():
for tx in block['tx']:
txid = tx['txid']
height = block['index']
for vin in tx['vin']:
vins.append([vin, txid, height])
for vout in tx['vout']:
vouts.append([vout, txid, height])
if 'claims' in tx.keys():
for claim in tx['claims']:
claims.append([claim, txid, height])
if vins:
await asyncio.wait(
[self.update_a_vin(*vin) for vin in vins])
if vouts:
await asyncio.wait(
[self.update_a_vout(*vout) for vout in vouts])
if claims:
await asyncio.wait(
[self.update_a_claim(*claim) for claim in claims])
#cache update addresses
if stop == current_height and 1 == len(self.processing):
uas = []
vinas = await asyncio.gather(
*[self.get_address_from_vin(vin[0]) for vin in vins])
voutas = [vout[0]['address'] for vout in vouts]
uas = list(set(vinas + voutas))
await self.update_addresses(max_height, uas)
time_b = CT.now()
logger.info(
'reached %s ,cost %.6fs to sync %s blocks ,total cost: %.6fs'
% (max_height, time_b - time_a, stop - self.start,
time_b - START_TIME))
await asyncio.wait([
self.update_block(block) for block in self.cache.values()
])
await self.update_state(max_height)
self.start = max_height + 1
del self.processing
del self.cache
self.processing = []
self.cache = {}
else:
await asyncio.sleep(0.5)
% (max_height, time_b - time_a, stop - self.start,
time_b - START_TIME))
await asyncio.wait([
self.update_block(block) for block in self.cache.values()
])
await self.update_state(max_height)
self.start = max_height + 1
del self.processing
del self.cache
self.processing = []
self.cache = {}
else:
await asyncio.sleep(0.5)
if __name__ == "__main__":
START_TIME = CT.now()
logger.info('STARTING...')
mongo_uri = C.get_mongo_uri()
neo_uri = C.get_neo_uri()
mongo_db = C.get_mongo_db()
tasks = C.get_tasks()
loop = asyncio.get_event_loop()
crawler = Crawler(mongo_uri, mongo_db, neo_uri, loop, tasks)
try:
loop.run_until_complete(crawler.crawl())
except Exception as e:
logger.error('LOOP EXCEPTION: %s' % e)
finally:
loop.close()
async def crawl(self):
self.start = await self.get_history_state()
self.start += 1
while True:
current_height = await self.get_block_count()
time_a = CT.now()
if self.start < current_height:
stop = self.start + self.max_tasks
if stop >= current_height:
stop = current_height
self.processing.extend([i for i in range(self.start, stop)])
max_height = max(self.processing)
min_height = self.processing[0]
await asyncio.wait(
[self.cache_block(h) for h in self.processing])
if self.processing != sorted(self.cache.keys()):
msg = 'cache != processing'
logger.error(msg)
sys.exit(1)
txids = []
for block in self.cache.values():
for tx in block['tx']:
for vin in tx['vin']:
txids.append(vin['txid'])
txids = list(set(txids))
if txids:
await asyncio.wait(
[self.cache_utxo_vouts(txid) for txid in txids])
if sorted(txids) != sorted(self.cache_utxo.keys()):
msg = 'cache utxo error'
logger.error(msg)
sys.exit(1)
vins = []
vouts = []
for block in self.cache.values():
block_time = block['time']
for tx in block['tx']:
utxo_dict = {}
for vin in tx['vin']:
utxo = self.cache_utxo[vin['txid']][vin['vout']]
key = utxo['asset'] + '_' + utxo['address']
if key in utxo_dict.keys():
utxo_dict[key]['value'] = CT.sci_to_str(
str(
D(utxo_dict[key]['value']) +
D(utxo['value'])))
else:
utxo_dict[key] = utxo
vout_dict = {}
for vout in tx['vout']:
key = vout['asset'] + '_' + vout['address']
if key in vout_dict.keys():
vout_dict[key]['value'] = CT.sci_to_str(
str(
D(vout_dict[key]['value']) +
D(vout['value'])))
else:
vout_dict[key] = vout
if 1 == len(utxo_dict) == len(
vout_dict) and utxo_dict.keys(
) == vout_dict.keys():
key = list(utxo_dict.keys())[0]
if utxo_dict[key]['value'] == vout_dict[key][
'value']:
continue
utxos = list(utxo_dict.values())
for i in range(len(utxos)):
utxo = utxos[i]
key = utxo['asset'] + '_' + utxo['address']
if key in vout_dict.keys():
if D(utxo['value']) > D(
vout_dict[key]['value']):
utxo['value'] = CT.sci_to_str(
str(
D(utxo['value']) -
D(vout_dict[key]['value'])))
del vout_dict[key]
vins.append([utxo, tx['txid'], i, block_time])
voutx = list(vout_dict.values())
for k in range(len(voutx)):
vout = voutx[k]
vouts.append([vout, tx['txid'], k, block_time])
if vins:
await asyncio.wait(
[self.update_a_vin(*vin) for vin in vins])
if vouts:
await asyncio.wait(
[self.update_a_vout(*vout) for vout in vouts])
time_b = CT.now()
logger.info(
'reached %s ,cost %.6fs to sync %s blocks ,total cost: %.6fs'
% (max_height, time_b - time_a, stop - self.start,
time_b - START_TIME))
await self.update_history_state(max_height)
self.start = max_height + 1
del self.processing
del self.cache
del self.cache_utxo
self.processing = []
self.cache = {}
self.cache_utxo = {}
else:
await asyncio.sleep(0.5)
def solveReviewPage(asin, rank, url, fetchDate, bookPublishDate):
hlre = re.compile(
r'^(\d+) of (\d+) people found the following review helpful')
html = MyHtml.getHtml(url)
print "solving Review Page"
countOfReviews=int(html.xpath('.//div[@id="cm_cr-product_info"]/div/div[1]/div[2]/span')[0].text.strip())
if countOfReviews>0:
divWholeReviewList = html.xpath('.//div[@id="cm_cr-review_list"]')[0]
divReviewList = divWholeReviewList.xpath('./div[@id]')
print divReviewList
for divReview in divReviewList:
aReview = Review()
rank += 1
aReview.helpfulRank = rank
aReview.asin = asin
aReview.reviewID = divReview.attrib['id']
# helpful line
parentNode=divReview.xpath('.//span[@class="a-size-base cr-vote"]/span[1]/span[1]')
print "helpful Match",parentNode
helpfulMatch=None
if parentNode is not None:
match1 = divReview.xpath('.//span[@class="a-size-base cr-vote"]/span[1]/span[1]')
if match1 is not None and len(match1)>0:
if match1[0].text is not None:
helpfulMatch=hlre.match(match1[0].text.strip())
else:
match2=divReview.xpath('.//span[@class="a-size-base cr-vote"]/span[1]/span[1]/span[1]')
if match2 is not None and len(match2)>0:
if match2[0].text is not None:
helpfulMatch=hlre.match(match2[0].text.strip())
print helpfulMatch
if helpfulMatch:
aReview.helpful = int(helpfulMatch.group(1))
aReview.total = int(helpfulMatch.group(2))
aReview.helpfulness = aReview.helpful * \
100 / aReview.total / 100.0
else:
aReview.helpful=0
aReview.total=0
aReview.helpfulness=0
del helpfulMatch
print "getting rate data"
rateData = divReview.xpath('.//span[@class="a-icon-alt"]')[0].text.strip()
aReview.rate=rateData.split(' ')[0].strip()
aReview.title = divReview.xpath('.//a[@class="a-size-base a-link-normal review-title a-color-base a-text-bold"]')[0].text.strip()
print "getting reviewerId"
reviewer = divReview.xpath('.//span[@class="a-size-base a-color-secondary review-byline"]/a')
if reviewer is not None and len(reviewer)>0:
aReview.reviewerID=reviewer[0].attrib['href'].split('/')[4].split('?')[0]
print "reviewerId",aReview.reviewerID
aReview.date = CommonTool.strToDate(divReview.xpath('./div[@class="a-row"]/span[4]')[0].text.strip())
aReview.elapsedDate = (fetchDate - aReview.date).days
print bookPublishDate
if bookPublishDate=='N/A':
aReview.reviewBookDate='N/A'
else:
aReview.reviewBookDate = (aReview.date - (bookPublishDate)).days
# format line
try:
strFormat = divReview[3].xpath('./a[1]')[0].text.strip()
aReview.fromFormat = strFormat.split(' ')[1]
except IndexError:
aReview.fromFormat = ''
spanVerifiedPurchase = divReview.xpath('.//span[@class="a-size-mini a-color-state a-text-bold"]')
if spanVerifiedPurchase:
spanVerifiedPurchase=spanVerifiedPurchase[0].text.strip()
if spanVerifiedPurchase=="Verified Purchase":
aReview.verified = 1
else:
aReview.verified = 0
# review text line
divReviewText = divReview.xpath('.//div[@class="a-row review-data"]/span')[0]
aReview.description = filtTag.filter_tags(
etree.tostring(divReviewText).strip()).strip()
aReview.description = aReview.description.replace('\n', '<br />')
del divReviewText
# review comments line
aReview.numOfComments = CommonTool.strToInt(
divReview.xpath('.//div[@class="a-row a-spacing-top-small review-comments"]/div/a/span/span[1]')[0].text.strip())
aReview.getComments()
saveReview(review=aReview)
# try:
# reviewer = Reviewer.loadReviewer(aReview.reviewerID)
# aReview.lastReviewRank = reviewer.getPreBookReviewRanking(
# aReview.reviewID)
# except Exception, e:
# sys.stderr.write(str(e) + '\n')
# sys.stderr.write('lastReviewRank not found! url: {0} id: {1} \
# reviewerID: {2}\n'.format(
# url, aReview.reviewID, aReview.reviewerID))
# import traceback
# traceback.print_exc()
# end of for
# end of else
return rank
async def crawl(self):
self.start = await self.get_asset_state()
self.start += 1
while True:
current_height = await self.get_block_count()
time_a = CT.now()
if self.start < current_height:
stop = self.start + self.max_tasks
if stop >= current_height:
stop = current_height
self.processing.extend([i for i in range(self.start, stop)])
max_height = max(self.processing)
min_height = self.processing[0]
await asyncio.wait(
[self.cache_block(h) for h in self.processing])
if self.processing != sorted(self.cache.keys()):
msg = 'cache != processing'
logger.error(msg)
sys.exit(1)
global_assets = {}
nep5_assets = {}
for block in self.cache.values():
block_time = block['time']
for tx in block['tx']:
if 'RegisterTransaction' == tx['type']:
global_assets[tx['txid']] = tx['asset']
global_assets[tx['txid']]['time'] = block_time
if 'InvocationTransaction' == tx[
'type'] and 490 <= int(float(tx['sys_fee'])):
if tx['script'].endswith(
'68134e656f2e436f6e74726163742e437265617465'
):
try:
asset = self.parse_script(tx['script'])
except Exception as e:
print('parse error:', e)
continue
asset['time'] = block_time
nep5_assets[asset['contract']] = asset
if global_assets:
await asyncio.wait([
self.update_a_global_asset(*i)
for i in global_assets.items()
])
if nep5_assets:
await asyncio.wait([
self.update_a_nep5_asset(*i)
for i in nep5_assets.items()
])
time_b = CT.now()
logger.info(
'reached %s ,cost %.6fs to sync %s blocks ,total cost: %.6fs'
% (max_height, time_b - time_a, stop - self.start,
time_b - START_TIME))
await self.update_asset_state(max_height)
self.start = max_height + 1
del self.processing
del self.cache
self.processing = []
self.cache = {}
else:
await asyncio.sleep(0.5)
self.paperbackPrice = 0
priceList = divCenterCol.find(".//div[@id='tmmSwatches']/ul")
if priceList is None:
priceList = divCenterCol.xpath(
".//div[@id='twister']/div/span[@class='a-declarative']/table/tr\
")
for price in priceList:
try:
priceType = price.xpath(
'./td[@class="dp-title-col"]/*[@class="title-text"]/span\
')[0].text.strip()
priceValue = price.xpath(
"./td[@class='a-text-right dp-price-col']//span")[0]\
.text.strip()
if cmp(priceType, 'Kindle') == 0:
self.kindlePrice = CommonTool.strToFloat(priceValue)
elif cmp(priceType, 'Hardcover') == 0:
self.hardcoverPrice = CommonTool.strToFloat(priceValue)
elif cmp(priceType, 'Paperback') == 0:
self.paperbackPrice = CommonTool.strToFloat(priceValue)
except Exception, e:
pass
else:
priceList = priceList.xpath(".//li")
for priceLi in priceList:
spans = priceLi.xpath("./span/span/span/a/span")
priceType = spans[0].text.strip()
priceValue = spans[1]
if priceValue.find("./span") is not None:
priceValue = priceValue.find("./span").text.strip()
else:
def printData(self):
with open("../data/" + self.fetchDate.isoformat() + "/dataAll.txt",
"w") as fout:
ct = CommonTool(fout)
fout.write("\t".join(self.tableHeadList))
fout.write('\n')
fout.flush()
for i, reviewID in enumerate(self.reviewList):
if reviewID == '':
continue
print 'solve review {0} of {1}: {2}'.format(
i, len(self.reviewList), reviewID)
review = Review.loadReview(reviewID)
book = Book.loadBookByAsin(review.asin)
reviewer = Reviewer.loadReviewer(review.reviewerID)
ct.write(reviewID)
ct.write(review.asin)
ct.write(review.reviewerID)
ct.write(reviewer.rName)
ct.write(reviewer.tRev1)
ct.write(reviewer.tRev10)
ct.write(reviewer.tRev50)
ct.write(reviewer.tRev100)
ct.write(reviewer.tRev500)
ct.write(reviewer.tRev1000)
ct.write(reviewer.tRevHall)
ct.write(reviewer.vVoice)
ct.write(review.verified)
ct.write(review.rate)
ct.write(review.title)
ct.write(review.date)
ct.write(review.fetchDate)
ct.write(review.reviewBookDate)
ct.write(review.elapsedDate)
ct.write(review.helpful)
ct.write(review.total)
ct.write(review.helpfulness)
ct.write(review.helpfulRank)
ct.write(review.timeRank)
#ct.write(review.top1Percent)
#ct.write(review.top5Percent)
#ct.write(review.top10Percent)
ct.write(review.description)
ct.write(review.numOfComments)
ct.write(review.comment)
#ct.write(review.isQuoteTable)
ct.write(review.lastReviewRank)
ct.write(book.url)
ct.write(book.tag)
ct.write(book.allowPreview)
ct.write(book.binding)
ct.write(book.publishDate)
ct.write(book.author)
ct.write(book.authorInfo)
ct.write(book.rate)
ct.write(book.numOfReviews)
ct.write(book.kindlePrice)
ct.write(book.hardcoverPrice)
ct.write(book.paperbackPrice)
ct.write(book.bookDsc)
ct.write(book.listPrice)
ct.write(book.pages)
ct.write(book.isbn10)
ct.write(book.isbn13)
ct.write(book.subrank)
ct.write(book.hasEditorialReview)
ct.write(book.editorialReview)
#ct.write(book.hasQuoteTable)
ct.write(reviewer.email)
ct.write(reviewer.webPage)
ct.write(reviewer.hasPhoto)
ct.write(reviewer.rNum)
ct.write(reviewer.helpRate)
ct.write(reviewer.hVote)
ct.write(reviewer.tVote)
ct.write(reviewer.avgRate)
ct.write(reviewer.fRevTime)
ct.write(reviewer.lRevTime)
ct.write(reviewer.duration)
if reviewer.rReal == "N/A":
ct.write(0)
else:
ct.write(1)
if reviewer.location == "N/A":
ct.write(0)
else:
ct.write(1)
if reviewer.aboutMe == "N/A":
ct.write(0)
else:
ct.write(1)
if reviewer.interest == "N/A":
ct.write(0)
else:
ct.write(1)
ct.write(review.fromFormat)
# if review.fromFormat == "Hardcover":
# ct.write(0)
# elif review.fromFormat == "Paperback":
# ct.write(1)
# else:
# ct.write(2)
if reviewer.rRank == "N/A":
ct.write(0)
else:
ct.write(reviewer.rRank)
ct.writeln(book.rank)
def script_to_hash(unhex):
intermed = hashlib.sha256(unhex).digest()
return CT.big_or_little(
hexlify(hashlib.new('ripemd160',
intermed).digest()).decode('ascii'))
def hex_to_num_str(cls, hs):
bs = unhexlify(hs)
return CT.sci_to_str(str(D(cls.bytes_to_num(bs)) / 100000000))
def getPreviousReviewedBook(self,reviewerId):
initUrl="http://www.amazon.com/gp/cdp/member-reviews/"+reviewerId
self.allRevLink=initUrl
html=MyHtml.getHtml(initUrl)
ftable=html.xpath('.//body/table[2]')[0]
pages=ftable.xpath('./tr/td[2]/table[1]/tr[1]/td[2]/b/a[last()]')
if pages is not None and len(pages)>0:
totalPages=pages[0].text.strip()
else:
totalPages=1
strPages=str(totalPages)
print strPages
if "-" in strPages:
totalPages=totalPages.split('-')
print "totalPages",totalPages
totalPages=totalPages[1]
else:
totalPages=totalPages
print totalPages,"totalPages"
sortBy='MostRecentReview'
j=1
self.counter=0
flag=0
for j in range(1,(int(totalPages)+1)):
baseUrl="http://www.amazon.com/gp/cdp/member-reviews/"+reviewerId
baseUrl=baseUrl+ \
'?pageNumber={}&sortBy={}'.format(str(j), sortBy)
print baseUrl,j,totalPages
html=MyHtml.getHtml(baseUrl)
ftable=html.xpath('.//body/table[2]')[0]
mainTable=ftable.xpath('./tr/td[2]/table[2]/tr[@valign="top"]')
for row in mainTable:
if row is not None:
isBook=row.xpath('./td[5]/table/tr[2]/td/b')
if isBook is not None and len(isBook)>0:
if isBook[0].text is not None and flag==0:
edition=isBook[0].text.strip()
if "Edition" in edition:
print "got the previous book"
flag=1
reviewdate=row.xpath('./following-sibling::*')
reviewdate=reviewdate[0].xpath('.//nobr')
if reviewdate:
reviewdate=reviewdate[0].text.strip()
print "got the reviewDate",reviewdate
self.previousBookReviewDate=CommonTool.strToDate(reviewdate)
#to get link of the previous reviewedbook
url=row.xpath('./td[5]/table/tr[1]/td/b/a')[0].attrib['href']
asin=Book.getAsinFromUrl(url)
previousBook=Book.loadBookByAsin(asin)
print "asinofPrevious",asin
print "previousBook",previousBook
self.previousBookPublishDate=previousBook.publishDate
if j==1 and self.lRevTime=='':
reviewdate=mainTable[0].xpath('./following-sibling::*')
reviewdate=reviewdate[0].xpath('.//nobr')
print reviewdate,"lRevtime"
if reviewdate:
reviewdate=reviewdate[0].text.strip()
self.lRevTime=CommonTool.strToDate(reviewdate)
print "value of j",j
if j==int(totalPages) and self.fRevTime=='':
print "inside frevtime loop"
reviewdate=mainTable[-1].xpath('./following-sibling::*')
reviewdate=reviewdate[0].xpath('.//nobr')
print reviewdate,"fRevtime"
if reviewdate:
reviewdate=reviewdate[0].text.strip()
self.fRevTime=CommonTool.strToDate(reviewdate)
# rate
rateObj = row.xpath("./following-sibling::*")
rate = 'N/A'
if len(rateObj) != 0:
rateObj1 = rateObj[0].xpath(".//img")
title = rateObj1[0].attrib['title']
rate = title.split("out")[0].strip()
self.sum = self.sum + float(rate)
j=j+1
#end of inner for loop
print "sum",self.sum
if self.rNum is not 0:
self.avgRate=self.sum/self.rNum
self.avgRate=round(self.avgRate,2)
if self.lRevTime=='' or self.fRevTime=='':
duration=0
else :
duration = (self.lRevTime-self.fRevTime).days
self.duration=int(duration)
def solveProfileUp(self):
profile = self.html.xpath("//div[@class='a-row profile-details']")
if len(profile) == 0:
return
else:
profile = profile[0]
# Reviewer Name
self.rName = self.html.xpath(
".//div[@class='a-section']/h1")[0].text.strip()
if len(self.rName) == 0:
self.rName = "N/A"
# Reviewer Ranking
rRank = profile.xpath(".//div[@class='profile-info']")
for rank in rRank:
if len(rRank) != 0:
rRank = rank.xpath(".//div[@class='a-row']/span[@class='a-size-large a-text-bold']")
if len(rRank) != 0:
rRank = rRank[0].text.strip()
if len(rRank) != 0:
#rRank=rRank.split(':')[1]
self.rRank = rRank
self.rRank = self.rRank.replace('#', '')
self.rRank = CommonTool.strToInt(self.rRank)
else:
self.rRank = 'N/A'
else:
print "entered else in ranking"
rRank=profile.xpath(".//span[@class='a-size-small a-color-secondary']")
print rRank
for rank in rRank:
if "ranking" in rank.text:
rRank=rank
print "aranking ",rRank
if len(rRank)> 0 and rRank[0].text is not None:
rRank=rRank[0].text.strip()
if "#" in rRank:
rRank=rRank.split('#')
print "rank",rRank
self.rRank = rRank[1]
self.rRank = CommonTool.strToInt(self.rRank)
else:
self.rRank = 'N/A'
else:
self.rRank = 'N/A'
# Top Reviewer && Vine Voice
self.tRev1 = 0
self.tRev10 = 0
self.tRev50 = 0
self.tRev100 = 0
self.tRev500 = 0
self.tRev1000 = 0
self.tRevHall = 0
self.rReal=0
#self.vVoice = '0'
tRev = profile.xpath(
".//span[@class='a-color-link pr-c7y-badge a-text-bold']")
if len(tRev) != 0:
temp = tRev[0].text.strip()
if temp.find('#1 REVIEWER') != -1:
self.tRev1 = 1
elif temp.find('TOP 10 REVIEWER') != -1:
self.tRev10 = 1
elif temp.find('TOP 50 REVIEWER') != -1:
self.tRev50 = 1
elif temp.find('TOP 100 REVIEWER') != -1:
self.tRev100 = 1
elif temp.find('TOP 500 REVIEWER') != -1:
self.tRev500 = 1
elif temp.find('TOP 1000 REVIEWER') != -1:
self.tRev1000 = 1
elif temp.find('HALL OF FAME') != -1:
self.tRevHall = 1
#elif temp.find('VINE VOICE') != -1:
#self.vVoice = 1
# INTEREST
self.interest = profile.xpath(
".//div[@class='a-row a-spacing-medium profile-interests']")
if len(self.interest) == 0:
self.interest = 'N/A'
# print '(interest) No a-row a-spacing-medium profile-interests is
# found!'
else:
self.interest = self.interest[0].xpath(
"./div/span[@class='a-size-small']")[0].text.strip()
self.interest = self.interest.replace('\r', '')
self.interest = self.interest.replace('\n', '<br>')
# ABOUT ME
abtMe = profile.xpath(
".//span/text()[normalize-space(.)='About']/parent::*/\
following-sibling::div/div[1]/span/p")
print abtMe,"abtme"
if abtMe is not None and len(abtMe)>0:
for p in abtMe:
about =p.text.strip()\
.replace('\r', '').replace('\n', '<br />')
self.aboutMe=''
self.aboutMe=self.aboutMe+about
#except LookupError:
#self.aboutMe = 'N/A'
# Email && webpage
link1 = profile.xpath(".//div[@class='a-row break-word pr-link']/a")
if len(link1) == 0:
# print '(email) No a-size-small found!'
self.email = 0
else:
# self.email = link1[0].text.strip()
self.email = 1
link2 = profile.xpath(".//div[@class='a-row customer-website pr-link']/a/span")
if len(link2) == 0:
self.webPage = 0
else:
self.webPage = 1
# rNum
rNum = profile.xpath(".//div[@class='a-column a-span7 pr-link']/a/span")
if len(rNum) == 0:
self.rNum = 0
else:
rNum = rNum[0].text.strip()
if "Reviews" in rNum:
print rNum
rNum = rNum.split('(')
rNum=rNum[1]
rNum=rNum.split(')')
rNum=rNum[0]
else:
rNum='0'
self.rNum = CommonTool.strToInt(rNum)
# helpRate
helpful = profile.xpath(".//div[@class='a-row customer-helpfulness']")
if len(helpful) == 0:
# print '(helpful) No a-size-large a-text-bold found!'
self.helpRate = 0.0
else:
self.helpRate = helpful[0].xpath(
".//span[@class='a-size-large a-text-bold']")
if len(self.helpRate) == 0:
# print '(helpRate) No a-size-large a-text-bold found!'
self.helpRate = 0.0
else:
self.helpRate = self.helpRate[0].text.strip()
self.helpRate = int(self.helpRate[:-1]) / 100.0
# hVote && tVote
votes = profile.xpath(
"./span/div/div/div/span[@class='a-size-small a-color-secondary']")
if len(votes) == 0:
# print '(votes) No a-size-small a-color-secondary found!'
self.hVote = 0
self.tVote = 0
else:
votes = votes[0].text.strip()
votesList = votes.split(' of ')
self.hVote = votesList[0][1:]
self.tVote = votesList[1][:-1]
self.hVote = self.hVote.strip()
self.tVote = self.tVote.strip()
self.hVote = CommonTool.strToInt(self.hVote)
self.tVote = CommonTool.strToInt(self.tVote)
del votesList
def parse_return_type(cls, mark):
if isinstance(mark, str): mark = int(CT.big_or_little(mark), 16)
if isinstance(mark, int): return cls.get_arg_name(mark)
raise ValueError('wrong type for return {}'.format(mark))
