def mainFunction(product):
sites = xmlToDict.readXML('amazon')
for site in sites:
#product = 'Dell Inspiron 15 3521 Laptop (3rd Gen Ci3/ 4GB/ 500GB/ Win8)'
searchPage = readHTML(site['searchURL'] + (product))
productLinks = getLinkFromHTML(site['searchTags'], searchPage)
productPage = readHTML(site['prefix'] + productLinks[0])
if site['allReviewTags']:
reviewsLink = getLinkFromHTML(site['allReviewTags'], productPage)
else:
reviewsLink = productLinks
reviewPage = readHTML(site['prefix'] + reviewsLink[0])
reviewsHeading = getTagFromHTML(site['reviewHeading'], reviewPage)
reviewsText = getTagFromHTML(site['reviewText'], reviewPage)
reviewsUpvotes = getTagFromHTML(site['reviewUpvote'], reviewPage)
reviewStars = getTagFromHTML(site['reviewStarRating'], reviewPage)
nextPage = getLinkFromHTML(site['reviewNextPage'], reviewPage)
nextPage = [nextPage.pop()]
i = 0
while len(nextPage) > 0 and i < 2:
reviewPage = readHTML(site['prefix'] + nextPage[0])
reviewsHeading += getTagFromHTML(site['reviewHeading'], reviewPage)
reviewsText += getTagFromHTML(site['reviewText'], reviewPage)
reviewsUpvotes += getTagFromHTML(site['reviewUpvote'], reviewPage)
reviewStars += getTagFromHTML(site['reviewStarRating'], reviewPage)
nextPage = getLinkFromHTML(site['reviewNextPage'], reviewPage)
nextPage = [nextPage.pop()]
i += 1
reviews = []
for i in range(len(reviewsHeading)):
review = {}
review['heading'] = reviewsHeading[i]
review['upvotes'] = [
reviewsUpvotes[i].split(' ')[0],
reviewsUpvotes[i].split(' ')[2]
]
review['stars'] = reviewStars[i].split(' ')[0]
reviewTextSplit = reviewsText[i].split('.')
finalText = ''
for jj in reviewTextSplit:
if (jj.find('Amazon') == -1 and jj.find('amazon') == -1
and jj.find('delivered') == -1
and jj.find('delivery') == -1):
finalText += jj
finalText += '.'
review['text'] = finalText
reviews.append(review)
return reviews
def mainFunction(product):
sites = xmlToDict.readXML('flipkart')
for site in sites:
#product = 'Dell Inspiron 15 3521 Laptop (3rd Gen Ci3/ 4GB/ 500GB/ Win8)'
searchPage = readHTML(site['searchURL'] + (product))
productLinks = getLinkFromHTML(site['searchTags'], searchPage)
productPage = readHTML(site['prefix'] + productLinks[0])
if site['allReviewTags']:
reviewsLink = getLinkFromHTML(site['allReviewTags'], productPage)
else:
reviewsLink = productLinks
reviewPage = readHTML(site['prefix'] + reviewsLink[0])
reviewsHeading = getTagFromHTML(site['reviewHeading'], reviewPage)
reviewsText = getTagFromHTML(site['reviewText'], reviewPage)
reviewsUpvotes = getTagFromHTML(site['reviewUpvote'], reviewPage)
reviewStars = getTitleFromHTML(site['reviewStarRating'], reviewPage)
nextPage = getLinkFromHTML(site['reviewNextPage'], reviewPage)
if len(nextPage) > 0:
reviewPage = readHTML(site['prefix'] + nextPage[0])
reviewsHeading += getTagFromHTML(site['reviewHeading'], reviewPage)
reviewsText += getTagFromHTML(site['reviewText'], reviewPage)
reviewsUpvotes += getTagFromHTML(site['reviewUpvote'], reviewPage)
reviewStars += getTitleFromHTML(site['reviewStarRating'], reviewPage)
reviews = []
for i in range(len(reviewsHeading)):
review = {}
review['heading'] = reviewsHeading[i]
a = reviewsUpvotes[ 2 * i]
if reviewsUpvotes[ 2 * i].find('%') >= 0:
a = reviewsUpvotes[2 * i][0:reviewsUpvotes[ 2 * i].find('%')]
a = int(a)
b = int(reviewsUpvotes[2 * i + 1])
a = a * b / 100
review['upvotes'] = [ str(a), reviewsUpvotes[2 * i + 1]]
review['stars'] = reviewStars[i].split(' ')[0]
reviewTextSplit = reviewsText[i].split('.')
finalText = ''
for jj in reviewTextSplit:
if(jj.find('Flipkart') == -1 and jj.find('flipkart') == -1 and jj.find('delivered') == -1 and jj.find('delivery') == -1):
finalText += jj
finalText += '. '
review['text'] = finalText
reviews.append(review)
return reviews