def scrap(given_name: str, given_url, given_model_no=None):
"""
:param given_model_no:
:param given_name:
:param given_url:
:return: List of Scraped data, Data error count and Keyword
"""
if given_model_no is not None:
data = get_links(given_name, given_url, given_model_no)
else:
data = get_links(given_name, given_url)
if len(data) < 1:
return []
data_list = []
n = 1
for prd_data in data:
print(f'Getting data from link {n} of {len(data)}...')
n += 1
try:
t1 = datetime.now()
try:
title = clean_text(prd_data.find('.product--title-link')[0].text)
url = list(prd_data.absolute_links)[1]
except IndexError:
continue
try:
prd_price = clean_price(prd_data.find('.price--dollars')[0].text)
except Exception as e:
n = e
# print(f'\n{e} price\n{title}\n\n')
prd_price = '0'
try:
merchant = clean_text(prd_data.find('.product--seller')[0].text)
except Exception as e:
n = e
# print(f'\n\n{e} marchant \n{title}\n\n')
merchant = 'NA'
timestamp = datetime.now()
main = {
'name': title,
'price': prd_price,
'timestamp': timestamp,
'merchant': merchant,
'time': (datetime.now() - t1).total_seconds(),
'url': url
}
data_list.append(main)
except AttributeError:
pass
return data_list
def scrap(given_name: str, given_url, given_model_no=None):
"""
:param given_model_no:
:param given_name:
:param given_url:
:return: List of Scraped data, Data error count and Keyword
"""
if given_model_no is not None:
data = get_links(given_name, given_url, given_model_no)
else:
data = get_links(given_name, given_url)
if len(data) < 1:
return []
data_list = []
n = 1
for prd_data in data:
print(f'Getting data from link {n} of {len(data)}...')
n += 1
try:
t1 = datetime.now()
try:
title = clean_text(prd_data.find('.product-tile-name')[0].text)
url = prd_data.find('a.disp-block')[0].attrs['href']
except IndexError:
continue
try:
sku = prd_data.find('.product-tile-model')[0].text
except Exception as e:
exc = e
sku = ''
try:
prd_price = clean_price(
prd_data.find('.pricepoint-price')[0].text)
except Exception as e:
exc = e
# print(f'\n{e} price\n{title}\n\n')
prd_price = '0'
try:
merchant = clean_text(
prd_data.find('#sellerProfileTriggerId')[0].text)
except Exception as e:
exc = e
# print(f'\n\n{e} marchant \n{title}\n\n')
merchant = 'NA'
timestamp = datetime.now()
main = {
'name': title,
'price': prd_price,
'timestamp': timestamp,
'merchant': merchant,
'time': (datetime.now() - t1).total_seconds(),
'url': url,
'sku': sku,
}
data_list.append(main)
except AttributeError:
pass
return data_list
def scrap(given_name: str, given_url, given_model_no=None):
"""
:param given_model_no:
:param given_name:
:param given_url:
:return: List of Scraped data, Data error count and Keyword
"""
if given_model_no is not None:
links = get_links(given_name, given_url, given_model_no)
else:
links = get_links(given_name, given_url)
if len(links) < 1:
return []
data_list = []
n = 1
for link in links:
print(f'Getting data from link {n} of {len(links)}...')
n += 1
try:
t1 = datetime.now()
while True:
try:
session = HTMLSession()
prd_data = session.get(link)
break
except:
print('Error while getting data..\nRetrying in 2 seconds..')
time.sleep(2)
try:
title = clean_text(prd_data.html.find('#itemTitle')[0].text).replace('Details about ', '')
except IndexError:
continue
try:
sku = prd_data.html.find('#descItemNumber')[0].text
except Exception as e:
exc = e
sku = ''
try:
prd_price = clean_price(prd_data.html.find('#prcIsum')[0].text)
except Exception as e:
exc = e
# print(f'\n{e} price\n{title}\n\n')
prd_price = '0'
try:
merchant = clean_text(prd_data.html.find('span.mbg-nw')[0].text)
except Exception as e:
exc = e
# print(f'\n\n{e} marchant \n{title}\n\n')
merchant = 'NA'
timestamp = datetime.now()
main = {
'name': title,
'price': prd_price,
'timestamp': timestamp,
'merchant': merchant,
'time': (datetime.now() - t1).total_seconds(),
'url': link,
'sku': sku
}
data_list.append(main)
except AttributeError:
pass
return data_list
def scrap(given_name: str, given_url, given_model_no=None):
"""
:param given_model_no:
:param given_name:
:param given_url:
:return: List of Scraped data, Data error count and Keyword
"""
if given_model_no is not None:
links = get_links(given_name, given_url, given_model_no)
else:
links = get_links(given_name, given_url)
if len(links) < 1:
return []
data_list = []
number = 1
for link in links:
print(f'Getting data from link {number} of {len(links)}...')
url = link.find('.product-item-link')[0].attrs['href']
session = HTMLSession()
r = session.get(url)
number += 1
try:
t1 = datetime.now()
try:
title = clean_text(r.html.find('.page-title')[0].text)
except IndexError:
continue
try:
sku = r.html.find('.product-info-main>p>strong')[0].text
except Exception as e:
print(e)
sku = ''
try:
prd_price = clean_price(r.html.find('.price')[0].text)
except Exception as e:
n = e
# print(f'\n{e} price\n{title}\n\n')
prd_price = '0'
try:
merchant = clean_text(r.html.find('.product--seller')[0].text)
except Exception as e:
n = e
# print(f'\n\n{e} marchant \n{title}\n\n')
merchant = 'NA'
timestamp = datetime.now()
main = {
'name': title,
'price': prd_price,
'timestamp': timestamp,
'merchant': merchant,
'time': (datetime.now() - t1).total_seconds(),
'url': url,
'sku': sku
}
data_list.append(main)
except AttributeError:
pass
return data_list
def scrap(given_name: str, given_url, given_model_no=None):
"""
:param given_model_no:
:param given_name:
:param given_url:
:return: List of Scraped data, Data error count and Keyword
"""
if given_model_no is not None:
links = get_links(given_name, given_url, given_model_no)
else:
links = get_links(given_name, given_url)
if len(links) < 1:
return []
data_list = []
n = 1
for link in links:
print(f'Getting data from link {n} of {len(links)}...')
n += 1
try:
t1 = datetime.now()
while True:
try:
session = HTMLSession()
prd_data = session.get(link)
break
except:
print(
'Error while getting data..\nRetrying in 2 seconds..')
time.sleep(2)
try:
title = clean_text(prd_data.html.find('#productTitle')[0].text)
except IndexError:
continue
try:
table = prd_data.html.find('tr')
sku = ''
for row in table:
try:
th = row.text
if 'model' in th.lower() and 'number' in th.lower():
sku = row.find('td')[0].text
break
except IndexError:
continue
except Exception as e:
exc = e
sku = ''
try:
prd_price = clean_price(
prd_data.html.find('#price_inside_buybox')[0].text)
except Exception as e:
exc = e
# print(f'\n{e} price\n{title}\n\n')
prd_price = '0'
try:
merchant = clean_text(
prd_data.html.find('#sellerProfileTriggerId')[0].text)
except Exception as e:
exc = e
# print(f'\n\n{e} marchant \n{title}\n\n')
merchant = 'NA'
timestamp = datetime.now()
main = {
'name': title,
'price': prd_price,
'timestamp': timestamp,
'merchant': merchant,
'time': (datetime.now() - t1).total_seconds(),
'url': link,
'sku': sku,
}
data_list.append(main)
except AttributeError:
print('Error 0005')
return data_list
def scrap(given_name: str, given_url, given_model_no=None):
"""
:param given_model_no:
:param given_name:
:param given_url:
:return: List of Scraped data, Data error count and Keyword
"""
browser = webdriver.Firefox()
browser.minimize_window()
inp_name = given_name.replace(' ', '+').lower()
search_url = given_url.replace('{}', inp_name)
browser.get(search_url)
items = browser.find_elements_by_css_selector(
'.sc-bdVaJa.Tile-iqbpf7-0.fIkVYO')
print(f'{len(items)} Results Found for: {given_name}')
data_list = []
for prd_data in items:
try:
t1 = datetime.now()
try:
title = clean_text(
prd_data.find_elements_by_css_selector(
'.DefaultProductTile__ProductName-dfe2sm-1'
'.dRgJNf')[0].text)
url = prd_data.find_elements_by_css_selector(
'a')[0].get_attribute('href')
# print(title)
except IndexError:
continue
try:
p = prd_data.find_elements_by_css_selector(
'.ProductPrice__Wrapper-sc-1ye3dgu-0.guXOLt')[0].text
prd_price = clean_price(p)
if prd_price == '':
a = [][2]
except IndexError:
p = prd_data.find_elements_by_css_selector(
'.ProductPrice__Wrapper-sc-1ye3dgu-0.guXOLt')[0].text
prd_price = clean_price(p)
except Exception as e:
print(f'\n{e} price\n{title}\n\n')
prd_price = '0'
try:
merchant = clean_text(
prd_data.find_elements_by_css_selector('.get_merchant')
[0].text)
except Exception as e:
n = e
# print(f'\n\n{e} marchant \n{title}\n\n')
merchant = 'NA'
timestamp = datetime.now()
main = {
'name': title,
'price': prd_price,
'timestamp': timestamp,
'merchant': merchant,
'time': (datetime.now() - t1).total_seconds(),
'url': url,
'sku': False,
}
data_list.append(main)
except AttributeError:
pass
except Exception as e:
print(e, end=' AT GET DATA')
try:
browser.quit()
except Exception as e:
print(e)
pass
return data_list
def scrap(given_name: str, given_url, given_model_no=None):
"""
:param given_model_no:
:param given_name:
:param given_url:
:return: List of Scraped data, Data error count and Keyword
"""
browser = webdriver.Firefox()
# browser.minimize_window()
browser.get(given_url)
while True:
try:
input_field = browser.find_element_by_id('product-search-field')
break
except:
input('Solve captcha and press enter 1:')
input_field.clear()
for char in given_name:
input_field.send_keys(char)
sleep(0.3)
sleep(1)
input_field.send_keys(Keys.RETURN)
sleep(3)
while True:
try:
items = browser.find_elements_by_css_selector('._1umis')
break
except:
input('Solve captcha and press enter 2:')
print(f'{len(items)} Results Found for: {given_name}')
data_list = []
for prd_data in items:
try:
t1 = datetime.now()
try:
while True:
try:
title = clean_text(
prd_data.find_elements_by_css_selector('._1A_Xq')
[0].text)
url = browser.find_element_by_css_selector(
'._1A_Xq>a').get_attribute('href')
break
except Exception as e:
print(e)
input('Solve captcha and press enter 3:')
# print(title)
except IndexError:
continue
try:
print(prd_data.find_elements_by_css_selector('._2PrMB'))
p = prd_data.find_elements_by_css_selector('._2PrMB')[0].text
prd_price = clean_price(p)
except IndexError:
p = prd_data.find_elements_by_css_selector('._2PrMB')[0].text
prd_price = clean_price(p)
except Exception as e:
n = e
# print(f'\n{e} price\n{title}\n\n')
prd_price = '0'
try:
merchant = clean_text(
prd_data.find_elements_by_css_selector('.merchant')
[0].text)
except Exception as e:
n = e
# print(f'\n\n{e} marchant \n{title}\n\n')
merchant = 'NA'
timestamp = datetime.now()
main = {
'name': title,
'price': prd_price,
'timestamp': timestamp,
'merchant': merchant,
'time': (datetime.now() - t1).total_seconds(),
'url': url
}
data_list.append(main)
except AttributeError:
pass
except Exception as e:
print(e, end=' AT GET DATA')
try:
browser.quit()
except:
print('Clear..')
return data_list
def scrap(given_name: str, given_url, given_model_no=None):
"""
:param given_model_no:
:param given_name:
:param given_url:
:return: List of Scraped data, Data error count and Keyword
"""
browser = webdriver.Firefox()
browser.minimize_window()
inp_name = given_name.replace(' ', '+').lower()
search_url = given_url + inp_name
browser.get(search_url)
sleep(2)
items = browser.find_elements_by_css_selector(
'.ais-hits--item.ais-hits--item')
print(f'{len(items)} Results Found for: {given_name}')
data_list = []
for prd_data in items:
try:
t1 = datetime.now()
try:
title = clean_text(
prd_data.find_elements_by_css_selector(
'.ais-hit--title.product-tile__title')[0].text)
# print(title)
url = prd_data.find_elements_by_css_selector(
'.product-tile')[0].get_attribute('href')
except IndexError:
continue
try:
p = prd_data.find_elements_by_css_selector('span.sale')[0].text
prd_price = clean_price(p)
if prd_price == '':
a = [][2]
except IndexError:
p = prd_data.find_elements_by_css_selector(
'span.ais-hit--price.price')[0].text
prd_price = clean_price(p)
except Exception as e:
print(f'\n{e} price\n{title}\n\n')
prd_price = '0'
try:
merchant = clean_text(
prd_data.find_elements_by_css_selector('.merchant')
[0].text)
except Exception as e:
n = e
# print(f'\n\n{e} marchant \n{title}\n\n')
merchant = 'NA'
timestamp = datetime.now()
main = {
'name': title,
'price': prd_price,
'timestamp': timestamp,
'merchant': merchant,
'time': (datetime.now() - t1).total_seconds(),
'url': url,
'sku': False,
}
data_list.append(main)
except AttributeError:
pass
except Exception as e:
print(e, end=' AT GET DATA')
try:
browser.quit()
except Exception as e:
n = e
pass
return data_list
def scrap(given_name: str, given_url, given_model_no=None):
"""
:param given_model_no:
:param given_name:
:param given_url:
:return: List of Scraped data, Data error count and Keyword
"""
if given_model_no is not None:
links = get_links(given_name, given_url, given_model_no)
else:
links = get_links(given_name, given_url)
if len(links) < 1:
return []
data_list = []
number = 1
for link in links:
print(f'Getting data from link {number} of {len(links)}...')
url = link.find('.name.fn.l_mgn-tb-sm.l_dsp-blc')[0].attrs['href']
session = HTMLSession()
r = session.get(url)
number += 1
try:
t1 = datetime.now()
try:
title = clean_text(r.html.find('.product-name')[0].text)
sku = r.html.find('.product-id.meta.quiet.p_txt-sm')[-1].text
except IndexError:
continue
except Exception as e:
n = e
continue
try:
prd_price = clean_price(
r.html.find('.price-device>script')[0].text)
except Exception as e:
n = e
# print(f'\n{e} price\n{title}\n\n')
prd_price = '0'
try:
merchant = clean_text(r.html.find('#sellerProfile')[0].text)
except Exception as e:
n = e
merchant = 'NA'
timestamp = datetime.now()
main = {
'name': title,
'price': prd_price,
'timestamp': timestamp,
'merchant': merchant,
'time': (datetime.now() - t1).total_seconds(),
'url': url,
'sku': sku,
}
data_list.append(main)
except AttributeError:
pass
return data_list
