def main(directory, mainlink):
filename = "%s/complete_link_collection.txt" %(directory)
f = open(filename, "a+")
driver = phan_proxy.main(mainlink)
try:
driver.find_element_by_xpath("/html/body/div[2]/div/div/div/div/a/img").click()
logging.debug("clicked..................................................................")
except:
pass
page = driver.page_source
driver.delete_all_cookies()
driver.quit()
soup = BeautifulSoup(page, "html.parser")
link_list = soup.find_all("a", attrs={"class":"somn-track"})
for link in link_list:
link = link.get("href")
parsed = urlparse(link)
if len(parsed.netloc) == 0:
link = "http://www.snapdeal.com%s" %(link)
f.write(str(link) + "\n")
print link
f.close()
def main2(bl):
driver = phan_proxy.main(bl)
page = driver.page_source
#print page
#print driver.current_url
try:
time.sleep(2)
driver.find_element_by_id("jab-news").click()
logging.debug("jab-news....")
except:
pass
try:
time.sleep(1)
driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
logging.debug("scrolling... first")
return driver
except:
logging.debug("repeating...")
driver.delete_all_cookies()
driver.quit()
main2(bl)
def main(line):
print line
line2 = line.strip().split(",")
menulink = line2[0].strip()
menutitle = line2[1].strip()
catlink = line2[2].strip()
cattitle = line2[3].strip()
subcatlink = line2[4].strip()
subcatitle = line2[5].strip()
brandlink = line2[6].strip()
brandtite = line2[7].strip()
driver = phan_proxy.main(brandlink)
driver = driver_scroller(driver)
driver = sub_scroller(driver)
page = driver.page_source
soup = BeautifulSoup(page)
tag_srchresult = soup.find("div", attrs={"id": "searchResultsDiv"})
tag_product = tag_srchresult.find_all("p",
attrs={"class": "product_title"})
for al in tag_product:
print "%s%s" % ("http://www.homeshop18.com", str(
al.a.get("href")).strip())
def main(line):
print line
line2 = line.strip().split(",")
menulink = line2[0].strip()
menutitle = line2[1].strip()
catlink = line2[2].strip()
cattitle = line2[3].strip()
subcatlink = line2[4].strip()
subcatitle = line2[5].strip()
brandlink = line2[6].strip()
brandtite = line2[7].strip()
driver = phan_proxy.main(brandlink)
driver = driver_scroller(driver)
driver = sub_scroller(driver)
page = driver.page_source
soup = BeautifulSoup(page)
tag_srchresult = soup.find("div", attrs={"id":"searchResultsDiv"})
tag_product = tag_srchresult.find_all("p", attrs={"class":"product_title"})
for al in tag_product:
print "%s%s" %("http://www.homeshop18.com", str(al.a.get("href")).strip())
def supermain():
link = "http://www.snapdeal.com/products/mens-footwear-sports-shoes/?q=Wearability_s%3AFootball&sort=plrty&#plrty|"
link ="http://www.snapdeal.com/products/mens-footwear-casual-shoes?q=Price:399,7899&sort=rec"
driver = phan_proxy.main(link)
try:
driver.find_element_by_xpath("/html/body/div[2]/div/div/div/div/a/img").click()
logging.debug("clicked..................................................................")
except:
pass
driver = main(driver)
page = driver.page_source
soup = BeautifulSoup(page, "html.parser")
item_big_box_list = soup.find("div", attrs={"id":"products-main4"})
item_box_list = item_big_box_list.find_all("div", attrs={"class":"product_grid_row"})
for item_box in item_box_list:
item_sub_box_list = item_box.find_all("div", attrs={"class":"product_grid_cont gridLayout3"})
for item_sub_box in item_sub_box_list:
item_link = item_sub_box.find("a", attrs={"class":"hit-ss-logger somn-track prodLink"}).get("href")
print item_link
print len(item_box_list)
driver.delete_all_cookies()
driver.quit()
def main():
directory = "dir%s" % (time.strftime("%d%m%Y"))
try:
os.makedirs(directory)
except:
pass
f = open("to_extract.txt", "w+")
print >> f, directory
f.close()
f = open("extracted.txt", "a+")
print >> f, directory
f.close()
link = "http://www.homeshop18.com/all-stores.html"
driver = phan_proxy.main(link)
try:
WebDriverWait(driver, 1000).until(ajax_complete,
"Timeout waiting for page to load")
except WebDriverException:
pass
try:
driver.find_element_by_xpath("/html/body/div[7]/div/a").click()
except:
pass
try:
WebDriverWait(driver, 1000).until(ajax_complete,
"Timeout waiting for page to load")
except WebDriverException:
pass
driver = driver_scroller(driver)
page = driver.page_source
soup = BeautifulSoup(page)
tag_menuflyer = soup.find("div", attrs={"class": "bcMenuFlyer"})
tag_menu_lt = tag_menuflyer.find_all("a")
ml_mt = []
for lt in tag_menu_lt:
lt.get_text()
menulink = "%s%s" % ("http://www.homeshop18.com", str(
lt.get("href")).strip())
menutitle = str(lt.get_text()).strip()
ml_mt.append([menulink, menutitle])
mainthreading(ml_mt)
def main(line):
f = open("to_extract_cat.txt")
directory = f.read().strip()
f.close()
filename2 = "%s/%s" %(directory, "f_ct_cl_st_sl_tp_prt_em_im_wl.csv")
f2 = open(filename2, "a+")
line2 = line.strip().split(",")
line2 = map(str.strip, line2)
cattitle = line2[0]
catlink = line2[1]
subcattitle = line2[2]
subcatlink = line2[3]
tpe = line2[4]
prt = line2[5]
wl = line2[6]
img = line2[7]
driver = phan_proxy.main(wl)
try:
WebDriverWait(driver, 1000).until( ajax_complete, "Timeout waiting for page to load")
except WebDriverException:
pass
page = driver.page_source
tree = html.fromstring(page)
embedlink = tree.xpath("/html/body/div[2]/center/div/div/div[2]/iframe/@src")
embedlink2 = tree.xpath("/html/body/object/embed/@src")
embedlink3 = tree.xpath("/html/body/div[2]/center/div/div/div[2]/object/embed/@src")
if embedlink is not None:
print >>f2, ','.join([cattitle, catlink, subcattitle, subcatlink, tpe, prt, str(embedlink[0]).strip(), img, wl])
logging.debug([cattitle, catlink, subcattitle, subcatlink, tpe, prt, str(embedlink[0]).strip(), img, wl])
elif embedlink2 is not None:
print >>f2, ','.join([cattitle, catlink, subcattitle, subcatlink, tpe, prt, str(embedlink2[0]).strip(), img, wl])
logging.debug([cattitle, catlink, subcattitle, subcatlink, tpe, prt, str(embedlink2[0]).strip(), img, wl])
elif embedlink3 is not None:
print >>f2, ','.join([cattitle, catlink, subcattitle, subcatlink, tpe, prt, str(embedlink3[0]).strip(), img, wl])
logging.debug([cattitle, catlink, subcattitle, subcatlink, tpe, prt, str(embedlink3[0]).strip(), img, wl])
else:
f3 = open("page3_filmlink_embedlink_error2.txt", "a+")
print >>f3, line
f3.close()
driver.delete_all_cookies()
driver.quit()
f2.close()
def main():
directory = "dir%s" % (time.strftime("%d%m%Y"))
try:
os.makedirs(directory)
except:
pass
f = open("to_extract.txt", "w+")
print >> f, directory
f.close()
f = open("extracted.txt", "a+")
print >> f, directory
f.close()
link = "http://www.homeshop18.com/all-stores.html"
driver = phan_proxy.main(link)
try:
WebDriverWait(driver, 1000).until(ajax_complete, "Timeout waiting for page to load")
except WebDriverException:
pass
try:
driver.find_element_by_xpath("/html/body/div[7]/div/a").click()
except:
pass
try:
WebDriverWait(driver, 1000).until(ajax_complete, "Timeout waiting for page to load")
except WebDriverException:
pass
driver = driver_scroller(driver)
page = driver.page_source
soup = BeautifulSoup(page)
tag_menuflyer = soup.find("div", attrs={"class": "bcMenuFlyer"})
tag_menu_lt = tag_menuflyer.find_all("a")
ml_mt = []
for lt in tag_menu_lt:
lt.get_text()
menulink = "%s%s" % ("http://www.homeshop18.com", str(lt.get("href")).strip())
menutitle = str(lt.get_text()).strip()
ml_mt.append([menulink, menutitle])
mainthreading(ml_mt)
def main(directory, link, target, cate):
directory2 = "%s/%s/%s" %(directory, target, cate)
try:
os.makedirs(directory2)
except:
pass
filename = "%s/%s.doc" %(directory2, cate)
f = open(filename, "a+")
driver = phan_proxy.main(link)
driver = driver_scroller(driver)
page = driver.page_source
driver.delete_all_cookies()
driver.quit()
soup = BeautifulSoup(page, "html.parser")
item_box = soup.find("section", attrs={"id":"catalog"})
items_list = item_box.find_all("div", attrs={"class":"item"})
for item_tag in items_list:
sub_cate = item_tag.get("data-tag")
colour = item_tag.get("data-color")
price = item_tag.get("data-price")
gender = item_tag.get("data-gender")
sku = item_tag.get("data-option")
item_link = "http://zovi.com%s" %(item_tag.a.get("href"))
item_image = "http:%s" %(item_tag.a.img.get("data-original"))
item_size2 = item_tag.find("div", attrs={"class":"available-sizes"})
try:
item_size = item_size2.find_all("li", attrs={"class":""})
item_size = str(map(tag_text, item_size)).replace(",", " ")
except:
item_size = str(item_size2)
item_title = str(item_tag.find("div", attrs={"class":"title"}).get_text()).replace(",", " ").strip()
try:
item_sale = item_tag.find("span", attrs={"class":"tags visible sale"}).get_text().strip()
except:
item_sale = " "
item_info = [link, target, cate, sub_cate, colour, price, gender,
sku, item_link, item_image, item_size, item_title, item_sale]
f.write(str(map(str, item_info)) + "\n")
logging.debug(item_info)
f.close()
def main(line, directory):
line = ast.literal_eval(line)
line = map(str.strip, line)
menu = line[0]
submnlink = line[1]
submntitle = line[2]
catlink = line[3]
cattitle = line[4]
brandlink = line[-2]
brandtitle = line[-1]
start = brandtitle.find("(")
brandtitle = brandtitle[:start].strip()
dirtwo = "%s/%s/%s/%s/%s" %(directory, menu, submntitle, cattitle, brandtitle)
try:
os.makedirs(dirtwo)
except:
pass
filedoc = "%s/%s.doc" %(dirtwo, brandtitle)
filedocx = "%s/%s.docx" %(dirtwo, brandtitle)
f2 = open(filedoc, "a+")
f3 = open(filedocx, "a+")
driver = phan_proxy.main(brandlink)
driver = driver_scroller(driver)
driver = sub_scroller(driver)
page = driver.page_source
soup = BeautifulSoup(page, "html.parser")
tag_product = soup.find("div", attrs={"id":"products"})
tag_product_a = tag_product.find_all("a", attrs={"class":"pu-image fk-product-thumb "})
for al in tag_product_a:
itemlink = "%s%s" %("http://www.flipkart.com", str(al.get("href").strip()))
print >>f2, [menu, submnlink, submntitle, catlink, cattitle, brandlink, brandtitle, itemlink]
print >>f3, itemlink
print [menu, submnlink, submntitle, catlink, cattitle, brandlink, brandtitle, itemlink]
driver.delete_all_cookies()
driver.quit()
f2.close()
f3.close()
def main():
directory = "dir%s" %(time.strftime("%d%m%Y"))
f = open("to_extract.txt", "w+")
print >>f, directory
f.close()
f = open("extracted.txt", "a+")
print >>f, directory
f.close()
try:
os.makedirs(directory)
except:
pass
link = "http://www.jabong.com"
driver = phan_proxy.main(link)
try:
driver.find_element_by_id("jab-news").click()
except:
pass
page = driver.page_source
driver.close()
soup = BeautifulSoup(page)
tag_li = soup.find("li", attrs={"id":"qa-navigation0"})
h = HTMLParser.HTMLParser()
tag_li = h.unescape(str(tag_li))
tag_li = tag_li.replace("\n", " ").replace("<!--", " ").replace("-->", " ")
soup = BeautifulSoup(tag_li)
tag_a = soup.find_all("a")
menu_links = []
for l in tag_a:
try:
menulink = l.get("href")
menu_links.append(menulink)
except:
pass
main2(menu_links)
def wl_to_el(self, line):
driver = phan_proxy.main(line[-2])
page = driver.page_source
driver.quit()
tree = html.fromstring(page)
if len(tree.xpath("/html/body/center/table/tbody/tr[2]/td/iframe/@src")) != 0:
embedlink = tree.xpath("/html/body/center/table/tbody/tr[2]/td/iframe/@src")[0]
elif len(tree.xpath("/html/body/center/table/tbody/tr[2]/td/embed/@src")) != 0:
embedlink = tree.xpath("/html/body/center/table/tbody/tr[2]/td/embed/@src")[0]
elif len(tree.xpath("/html/body/div[2]/center/div/div/div[2]/object/embed/@src")) != 0:
embedlink = tree.xpath("/html/body/div[2]/center/div/div/div[2]/object/embed/@src")[0]
elif len(tree.xpath("/html/body/object/embed/@src")) != 0:
embedlink = tree.xpath("/html/body/object/embed/@src")[0]
elif len(tree.xpath("/html/body/div[2]/center/div/div/div[2]/iframe/@src")) != 0:
embedlink = tree.xpath("/html/body/div[2]/center/div/div/div[2]/iframe/@src")[0]
elif len(tree.xpath("/html/body/div/div[2]/div[3]/div[3]/div/input/@value")) != 0:
embedlink = tree.xpath("/html/body/div/div[2]/div[3]/div[3]/div/input/@value")
start = embedlink[0].find("src=")
end = embedlink[0].find('"', start + 5)
embedlink = embedlink[0][start + 5 : end].strip()
else:
embedlink = ""
try:
data = [
filter(None, line[0].split("/"))[3],
line[0],
line[1].split("/")[-1][:-5],
line[1],
line[2],
line[3],
embedlink,
line[-1],
line[-2],
]
self.f.write(",".join(data) + "\n")
logging.debug(("inserted....", embedlink))
except:
pass
def main(line):
filename2 = "dt_movie2.csv"
f2 = open(filename2, "a+")
line2 = line.strip().split(",")
line2 = map(str.strip, line2)
cattitle = line2[1]
catlink = line2[2]
subcattitle = line2[3]
subcatlink = line2[4]
tpe = line2[5]
prt = line2[6]
wl = line2[-3]
img = line2[-4]
wl = wl.replace('"', " ").strip()
driver = phan_proxy.main(wl)
page = driver.page_source
tree = html.fromstring(page)
embedlink = tree.xpath("/html/body/div[2]/center/div/div/div[2]/iframe/@src")
embedlink2 = tree.xpath("/html/body/object/embed/@src")
embedlink3 = tree.xpath("/html/body/div[2]/center/div/div/div[2]/object/embed/@src")
if embedlink3 is not None:
print >>f2, ','.join([cattitle, catlink, subcattitle, subcatlink, tpe, prt, str(embedlink3[0]).strip(), img, wl])
logging.debug([cattitle, catlink, subcattitle, subcatlink, tpe, prt, str(embedlink3[0]).strip(), img, wl])
elif embedlink2 is not None:
print >>f2, ','.join([cattitle, catlink, subcattitle, subcatlink, tpe, prt, str(embedlink2[0]).strip(), img, wl])
logging.debug([cattitle, catlink, subcattitle, subcatlink, tpe, prt, str(embedlink2[0]).strip(), img, wl])
elif embedlink is not None:
print >>f2, ','.join([cattitle, catlink, subcattitle, subcatlink, tpe, prt, str(embedlink[0]).strip(), img, wl])
logging.debug([cattitle, catlink, subcattitle, subcatlink, tpe, prt, str(embedlink[0]).strip(), img, wl])
else:
f3 = open("page3_filmlink_embedlink_error2.txt", "a+")
print >>f3, line
f3.close()
driver.delete_all_cookies()
driver.quit()
f2.close()
def main4(line, filename):
menulink = line[0]
menutitle = line[1]
driver = phan_proxy.main(menulink)
height = 0
loop = True
while loop is True:
logging.debug("scrolling...")
time.sleep(1)
driver.execute_script(
"window.scrollTo(0, document.body.scrollHeight);")
time.sleep(1)
heightnow = driver.execute_script("return $(document ).height();")
if heightnow == height:
loop = False
else:
height = heightnow
loop = True
page = driver.page_source
soup = BeautifulSoup(page)
tag_main_comp_holder = soup.find(
"div", attrs={"class": "campaignHolder mainCampaignHolder"})
tag_a = tag_main_comp_holder.find_all("a", attrs={"class": "indulgeLink"})
line2 = str(line).strip("[]").strip()
f = open(filename, "a+")
for al in tag_a:
clink = str(al.get("href")).strip()
catlink = "%s%s" % ("http://www.fashionandyou.com", clink)
cattitle = clink.replace("/", "").strip()
print >> f, ','.join([menulink, menutitle, catlink, cattitle])
logging.debug((line2, catlink, cattitle))
f.close()
def main():
directory = "dirflipkart%s" %(time.strftime("%d%m%Y"))
try:
os.makedirs(directory)
except:
pass
f = open("to_extractfilpkart", "w+")
f.write(directory)
f.close()
f2 = open("extractedflipkart", "a+")
f2.write(directory)
f2.close()
link = "http://www.flipkart.com/"
driver = phan_proxy.main(link)
page = driver.page_source
#soup = BeautifulSoup(page, "html.parser")
soup = BeautifulSoup(page)
tag_menu = soup.find_all("li", attrs={"class":"menu-l0 "})
menu_subl_subt = []
for menu in tag_menu:
menutitle = menu.get("data-key")
submenu = menu.find_all("li", attrs={"class":"heading"})
submenu_new = menu.find_all("li", attrs={"class":"new-heading"})
submenu.extend(submenu_new)
for l in submenu:
submenutitle = str(l.get_text()).strip()
submenulink = "%s%s" %("http://www.flipkart.com", str(l.a.get("href")).strip())
menu_subl_subt.append([menutitle, submenulink, submenutitle])
driver.delete_all_cookies()
driver.quit()
mainthread(menu_subl_subt)
def main4(line, filename):
menulink = line[0]
menutitle = line[1]
driver = phan_proxy.main(menulink)
height = 0
loop = True
while loop is True:
logging.debug("scrolling...")
time.sleep(1)
driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
time.sleep(1)
heightnow = driver.execute_script("return $(document ).height();")
if heightnow == height:
loop = False
else:
height = heightnow
loop = True
page = driver.page_source
soup = BeautifulSoup(page)
tag_main_comp_holder = soup.find("div", attrs={"class":"campaignHolder mainCampaignHolder"})
tag_a = tag_main_comp_holder.find_all("a", attrs={"class":"indulgeLink"})
line2 = str(line).strip("[]").strip()
f = open(filename, "a+")
for al in tag_a:
clink = str(al.get("href")).strip()
catlink = "%s%s" %("http://www.fashionandyou.com", clink)
cattitle = clink.replace("/", "").strip()
print >>f, ','.join([menulink, menutitle, catlink, cattitle])
logging.debug((line2, catlink, cattitle))
f.close()
def main(line):
line2 = line.strip().split(",")
sub_cat = line2[-1].strip()
cattitle = line2[-2].strip()
catlink = line2[-3].strip()
menutitle = line2[1].strip()
menulink = line2[0].strip()
driver = phan_proxy.main(catlink)
try:
WebDriverWait(driver, 1000).until( ajax_complete, "Timeout waiting for page to load")
except WebDriverException:
pass
if (sub_cat is not "None") and (sub_cat is not "All Categories") :
driver = sub_cat_select(driver, sub_cat)
driver = driver_scroller(driver)
page = driver.page_source
soup = BeautifulSoup(page)
tag_ul_product = soup.find("ul", attrs={"class":"products"})
tag_li_dis_block = tag_ul_product.find_all("li", attrs={"style" : re.compile(": block;")})
for al in tag_li_dis_block:
tag_al_a = al.find("a", attrs={"class":"productLink"})
if tag_al_a:
productlink = "%s%s" %("http://www.fashionandyou.com", str(tag_al_a.get("href")).strip())
print ','.join([menulink, menutitle, catlink, cattitle, sub_cat, productlink])
print len(tag_li_dis_block)
driver.delete_all_cookies()
driver.quit()
def main():
link = "http://www.snapdeal.com/"
page = phan_proxy.main(link)
#page = req_proxy.main(link)
f = open("code1_sourcebody.txt", "a+")
print >>f, page.encode("ascii", "ignore")
f.close()
soup = BeautifulSoup(page)
tag_nav = soup.find_all("li", attrs={"class":"navlink"})
menu_list = {}
for l in tag_nav:
menu = str(l.a.get_text()).strip()
menu_list[menu] = {}
tag_a = l.find_all("a", attrs={"class":"somn-track"})
for l2 in tag_a:
sub_menu = str(l2.get_text()).strip()
sub_menulink = str(l2.get("href")).strip()
menu_list[menu][sub_menu] = sub_menulink
f = open("code1_menu_sub_menu_link.txt", "w+")
print >>f, menu_list
f.close()
menu_list.clear()
print menu_list
del menu_list
def main(line):
filename2 = "dt_movie2.csv"
f2 = open(filename2, "a+")
line2 = line.strip().split(",")
line2 = map(str.strip, line2)
cattitle = line2[1]
catlink = line2[2]
subcattitle = line2[3]
subcatlink = line2[4]
tpe = line2[5]
prt = line2[6]
wl = line2[-3]
img = line2[-4]
wl = wl.replace('"', " ").strip()
driver = phan_proxy.main(wl)
page = driver.page_source
tree = html.fromstring(page)
embedlink = tree.xpath(
"/html/body/div[2]/center/div/div/div[2]/iframe/@src")
embedlink2 = tree.xpath("/html/body/object/embed/@src")
embedlink3 = tree.xpath(
"/html/body/div[2]/center/div/div/div[2]/object/embed/@src")
if embedlink3 is not None:
print >> f2, ','.join([
cattitle, catlink, subcattitle, subcatlink, tpe, prt,
str(embedlink3[0]).strip(), img, wl
])
logging.debug([
cattitle, catlink, subcattitle, subcatlink, tpe, prt,
str(embedlink3[0]).strip(), img, wl
])
elif embedlink2 is not None:
print >> f2, ','.join([
cattitle, catlink, subcattitle, subcatlink, tpe, prt,
str(embedlink2[0]).strip(), img, wl
])
logging.debug([
cattitle, catlink, subcattitle, subcatlink, tpe, prt,
str(embedlink2[0]).strip(), img, wl
])
elif embedlink is not None:
print >> f2, ','.join([
cattitle, catlink, subcattitle, subcatlink, tpe, prt,
str(embedlink[0]).strip(), img, wl
])
logging.debug([
cattitle, catlink, subcattitle, subcatlink, tpe, prt,
str(embedlink[0]).strip(), img, wl
])
else:
f3 = open("page3_filmlink_embedlink_error2.txt", "a+")
print >> f3, line
f3.close()
driver.delete_all_cookies()
driver.quit()
f2.close()
def main(line):
line = ast.literal_eval(line)
menu = line[0]
catlink = line[1]
cattitle = line[2]
scatlink = line[3]
scattitle = line[4]
driver = phan_proxy.main(scatlink)
driver = driver_scroller(driver)
page = driver.page_source
driver.delete_all_cookies()
driver.quit()
soup = BeautifulSoup(page)
tag_brand = soup.find("ul", id="filter_Brands")
tag_brand_li = tag_brand.find_all("li")
tag_brand_li = tag_brand_li[1:]
f = open("to_extractbagittoday", "a+")
directory = f.read().strip()
f.close()
filename = "%s/%s" %(directory, "f_mn_ct_ct_scl_sct_bt.txt")
f = open(filename, "a+")
bt_list2 = []
for bt in tag_brand_li:
bt_list2.append(str(bt.span.get_text()))
bt_list = map(str_lower_strip, bt_list2)
print bt_list
tag_pro_image = soup.find_all("div", attrs={"class":"product-image"})
for l in tag_pro_image:
product_link = "%s%s" %("http://www.bagittoday.com", str(l.find("a").get("href")).strip())
product_image = str(l.find("img").get("data-original")).strip()
product_title = str(l.find("img").get("title")).lower().strip()
#product_title_split = map(str_lower_strip, product_title.lower().split(" "))
#brand = list((Counter(bt_list) & Counter(product_title_split)).elements())
brand2 = map(functools.partial(re_line_match, line = product_title), bt_list)
brand = filter(None, brand2)
if len(brand) == 0 :
brand = "private"
else:
brand = brand[0].strip()
print >>f, [menu, catlink, cattitle, scatlink, scattitle, brand, product_link, product_image, product_title]
print [menu, catlink, cattitle, scatlink, scattitle, brand, product_link, product_image, product_title]
f.close()
def main(line):
print line
line2 = line.strip().split(",")
menulink = line2[0].strip()
menutitle = line2[1].strip()
catlink = line2[2].strip()
cattitle = line2[3].strip()
subcatlink = line2[4].strip()
subcatitle = line2[5].strip()
brandlink = line2[6].strip()
brandtite = line2[7].strip()
driver = phan_proxy.main(brandlink)
driver = driver_scroller(driver)
driver = sub_scroller(driver)
page = driver.page_source
soup = BeautifulSoup(page, "html.parser")
tag_srchresult = soup.find("div", attrs={"id":"searchResultsDiv"})
#tag_product = tag_srchresult.find_all("p", attrs={"class":"product_title"})
tag_product = tag_srchresult.find_all("p", attrs={"class":"product_image"})
f = open("to_extract.txt")
directory = f.read().strip()
f.close()
sub_dir = "%s/%s/%s/%s/%s" %(directory, menutitle, cattitle, subcatitle, brandtite)
try:
os.makedirs(sub_dir)
except:
pass
filename1 = "%s/%s.doc" %(sub_dir, brandtite)
filename2 = "%s/%s.docx" %(sub_dir, brandtite)
f = open(filename1, "a+")
f2 = open(filename2, "a+")
for al in tag_product:
#prolink = "%s%s" %("http://www.homeshop18.com", str(al.a.get("href")).strip())
prolink = "%s%s" %("http://www.homeshop18.com", str(al.a.get("href")).strip())
prolimg = str(al.a.img.get("data-original")).strip()
parsed = urlparse(prolimg)
prolimg = "%s%s" %("http://www.homeshop18.com", parsed.path)
print >>f, ",".join([menulink, menutitle, catlink, cattitle, subcatlink, subcatitle, brandlink,brandtite, prolink, prolimg])
print >>f2, prolink
def main():
directory = "dirbagittoday%s" % (time.strftime("%d%m%Y"))
try:
os.makedirs(directory)
except:
pass
f = open("to_extractbagittoday", "w+")
print >> f, directory
f.close()
f2 = open("extractedbagittoday", "a+")
print >> f2, directory
f2.close()
filename = "%s/%s" % (directory, "f_mn_sl_st_scl_sct.txt")
f = open(filename, "a+")
link = "http://www.bagittoday.com/"
driver = phan_proxy.main(link)
driver.refresh()
page = driver.page_source
driver.delete_all_cookies()
driver.quit()
soup = BeautifulSoup(page)
tag_menu = soup.find("ul", attrs={"id": "menu"})
tag_menu_li = tag_menu.find_all("li", attrs={"class": "first"})
req_menu = [
"Men", "Women", "Kids", "Electronics & Mobiles", "Home & Kitchen",
"Jewellery"
]
req_manu_obj = []
for al in tag_menu_li:
if str(al.a.get_text()).strip() in req_menu:
req_manu_obj.append(al)
req_menu_subcat = {}
for menu in req_manu_obj:
menu_sub_cat = menu.find_all("li", id=re.compile("subCat"))
req_menu_subcat[str(menu.a.get_text()).strip()] = menu_sub_cat
mn_scl_sct_ccatl_ccatt = {}
for k, v in req_menu_subcat.items():
sub_cat_likn_title = map(sub_cat_extraction, v)
mn_scl_sct_ccatl_ccatt[k] = sub_cat_likn_title
#print mn_scl_sct_ccatl_ccatt
for k, v in mn_scl_sct_ccatl_ccatt.items():
for scl_sct_cl_ct in v:
sl_st = scl_sct_cl_ct[0]
sl_st = sl_st.split(",")
sl = sl_st[0]
st = sl_st[1]
if scl_sct_cl_ct is None:
print >> f, [k, sl, st, sl, st]
print[k, sl, st, sl, st]
for cl_ct in scl_sct_cl_ct[1]:
cl = cl_ct.keys()[0]
ct = cl_ct.values()[0]
print >> f, [k, sl, st, cl, ct]
print[k, sl, st, cl, ct]
f.close()
def main(line):
line2 = line.strip().split(",")
sub_cat = line2[-1].strip()
cattitle = line2[-2].strip()
catlink = line2[-3].strip()
menutitle = line2[1].strip()
menulink = line2[0].strip()
f = open("to_extract.txt")
directory = f.read().strip()
f.close()
if sub_cat == "None":
sub_cat2 = cattitle
sub_dir = "%s/%s/%s/%s" %(directory, menutitle, cattitle, sub_cat2)
filename1 = "%s/%s.doc" %(sub_dir,sub_cat2)
filename2 = "%s/%s.docx" %(sub_dir,sub_cat2)
else:
sub_dir = "%s/%s/%s/%s" %(directory, menutitle, cattitle, sub_cat)
filename1 = "%s/%s.doc" %(sub_dir,sub_cat)
filename2 = "%s/%s.docx" %(sub_dir,sub_cat)
try:
os.makedirs(sub_dir)
except:
pass
f = open(filename1, "a+")
f2 = open(filename2, "a+")
driver = phan_proxy.main(catlink)
try:
WebDriverWait(driver, 1000).until( ajax_complete, "Timeout waiting for page to load")
except WebDriverException:
pass
if (sub_cat != "None") and (sub_cat != "All Categories") :
driver = sub_cat_select(driver, sub_cat)
driver = driver_scroller(driver)
page = driver.page_source
soup = BeautifulSoup(page)
tag_ul_product = soup.find("ul", attrs={"class":"products"})
tag_li_dis_block = tag_ul_product.find_all("li", attrs={"style" : re.compile(": block;")})
for al in tag_li_dis_block:
tag_al_a = al.find("a", attrs={"class":"productLink"})
if tag_al_a:
productlink = "%s%s" %("http://www.fashionandyou.com", str(tag_al_a.get("href")).strip())
print >>f, ','.join([menulink, menutitle, catlink, cattitle, sub_cat, productlink])
print >>f2 , productlink
logging.debug([menulink, menutitle, catlink, cattitle, sub_cat, productlink])
print len(tag_li_dis_block)
driver.delete_all_cookies()
driver.quit()
f.close()
f2.close()
def main(line):
line = ast.literal_eval(line)
menu = line[0]
catlink = line[1]
cattitle = line[2]
scatlink = line[3]
scattitle = line[4]
driver = phan_proxy.main(scatlink)
driver = driver_scroller(driver)
page = driver.page_source
driver.delete_all_cookies()
driver.quit()
soup = BeautifulSoup(page)
tag_brand = soup.find("ul", id="filter_Brands")
tag_brand_li = tag_brand.find_all("li")
tag_brand_li = tag_brand_li[1:]
f = open("to_extractbagittoday", "a+")
directory = f.read().strip()
f.close()
filename = "%s/%s" % (directory, "f_mn_ct_ct_scl_sct_bt.txt")
f = open(filename, "a+")
bt_list2 = []
for bt in tag_brand_li:
bt_list2.append(str(bt.span.get_text()))
bt_list = map(str_lower_strip, bt_list2)
print bt_list
tag_pro_image = soup.find_all("div", attrs={"class": "product-image"})
for l in tag_pro_image:
product_link = "%s%s" % ("http://www.bagittoday.com",
str(l.find("a").get("href")).strip())
product_image = str(l.find("img").get("data-original")).strip()
product_title = str(l.find("img").get("title")).lower().strip()
#product_title_split = map(str_lower_strip, product_title.lower().split(" "))
#brand = list((Counter(bt_list) & Counter(product_title_split)).elements())
brand2 = map(functools.partial(re_line_match, line=product_title),
bt_list)
brand = filter(None, brand2)
if len(brand) == 0:
brand = "private"
else:
brand = brand[0].strip()
print >> f, [
menu, catlink, cattitle, scatlink, scattitle, brand, product_link,
product_image, product_title
]
print[
menu, catlink, cattitle, scatlink, scattitle, brand, product_link,
product_image, product_title
]
f.close()
def main():
directory = "dirbagittoday%s" %(time.strftime("%d%m%Y"))
try:
os.makedirs(directory)
except:
pass
f = open("to_extractbagittoday", "w+")
print >>f, directory
f.close()
f2 = open("extractedbagittoday", "a+")
print >>f2, directory
f2.close()
filename = "%s/%s" %(directory, "f_mn_sl_st_scl_sct.txt")
f = open(filename, "a+")
link = "http://www.bagittoday.com/"
driver = phan_proxy.main(link)
driver.refresh()
page = driver.page_source
driver.delete_all_cookies()
driver.quit()
soup = BeautifulSoup(page)
tag_menu = soup.find("ul", attrs={"id":"menu"})
tag_menu_li = tag_menu.find_all("li", attrs={"class":"first"})
req_menu = ["Men", "Women", "Kids", "Electronics & Mobiles", "Home & Kitchen", "Jewellery"]
req_manu_obj = []
for al in tag_menu_li:
if str(al.a.get_text()).strip() in req_menu:
req_manu_obj.append(al)
req_menu_subcat = {}
for menu in req_manu_obj:
menu_sub_cat = menu.find_all("li", id = re.compile("subCat"))
req_menu_subcat[str(menu.a.get_text()).strip()] = menu_sub_cat
mn_scl_sct_ccatl_ccatt = {}
for k, v in req_menu_subcat.items():
sub_cat_likn_title = map(sub_cat_extraction, v)
mn_scl_sct_ccatl_ccatt[k] = sub_cat_likn_title
#print mn_scl_sct_ccatl_ccatt
for k, v in mn_scl_sct_ccatl_ccatt.items():
for scl_sct_cl_ct in v:
sl_st = scl_sct_cl_ct[0]
sl_st = sl_st.split(",")
sl = sl_st[0]
st = sl_st[1]
if scl_sct_cl_ct is None:
print >>f, [k, sl, st, sl, st]
print [k, sl, st, sl, st]
for cl_ct in scl_sct_cl_ct[1]:
cl = cl_ct.keys()[0]
ct = cl_ct.values()[0]
print >>f, [k, sl, st, cl, ct]
print [k, sl, st, cl, ct]
f.close()
