def get_image(price):
price_argo = read_csv(price)
list_image_dir = []
i = 1
for stuff in price_argo:
html = get_html(stuff['url_stuff'])
soup = BeautifulSoup(html, 'lxml')
try:
image_list = soup.find('div', id='product-gallery').find_all('a')
except:
image_list = soup.find('div', class_='image-border').find_all('a')
image_list_url = []
for image in image_list:
url_image = image.get('href')
if url_image in image_list_url:
break
image_list_url.append(url_image)
dir_for_image = os.path.join(
r'D:\tmp\python\python_parsing\parsing_ARGO', 'image',
stuff['category_name'],
stuff['name_stuff']).replace(' ', '_').replace('"', '')
while dir_for_image in list_image_dir:
dir_for_image = dir_for_image + '_' + str(i)
i += 1
os.makedirs(dir_for_image)
list_image_dir.append(dir_for_image)
for i, image in enumerate(image_list_url):
if image == '':
continue
with open(os.path.join(dir_for_image, '{}.jpg'.format(i)),
'wb') as image_file:
image_file.write(requests.get(image).content)
write_csv(stuff, dir_for_image + '\info.csv')
def GetFilmCatalog(ListData, num):
NameFile = r'D:\tmp\my_prod\Python\python\ParsingMobi711\MobiParsBk_mp.csv'
for Data in ListData:
html = get_html('https://mobi711.ru' + Data['Url'])
soup = BeautifulSoup(html, 'lxml')
try:
DivUrlFilmCatalog = soup.find_all('div',
class_='category no-description')
except AttributeError:
DivUrlFilmCatalog = []
if DivUrlFilmCatalog != []:
for Div in DivUrlFilmCatalog:
UrlFilmCatalog = 'https://mobi711.ru' + \
Div.find('div', class_='text').find('a').get('href')
Name = Div.find('div', class_='text').find('a').text
if Name == 'Защитные пленки и стекла':
break
else:
UrlFilmCatalog = ''
Name = ''
else:
UrlFilmCatalog = ''
data = {
'Brand': Data['Brand'],
'Model': Data['Model'],
'UrlModel': Data['Url'],
'UrlFilmCatalog': UrlFilmCatalog
}
write_csv(data, NameFile)
def get_stuff_info(list_stuff):
for stuff in list_stuff:
url_stuff = stuff['url_stuff']
html_stuff = get_html(url_stuff)
soup = BeautifulSoup(html_stuff, 'lxml')
text_info = soup.find('div', id='test').find_all('li')
size, color, cloth = '', '', ''
price = ''
try:
price = soup.find('div', class_='retail-price price-prod').text
except:
price = ''
for text_ in text_info:
cur_line_name = text_.find('span', class_='opts-lab').text
cur_line_val = text_.find('span', class_='opts-val').text
if cur_line_name == 'Размер:':
size = cur_line_val
elif cur_line_name == 'Цвет:':
color = cur_line_val
elif cur_line_name == 'Ткань:':
cloth = cur_line_val
data_stuff = {
'category_name': stuff['category_name'],
'name_stuff': stuff['name_stuff'],
'url_stuff': stuff['url_stuff'],
'size': size,
'color': color,
'cloth': cloth,
'price': price
}
print(data_stuff)
write_csv(data_stuff,
r'D:\tmp\my_prod\Python\python\parsing_ARGO\argo.csv')
def get_information():
data = {
'name_stuff': name_stuff,
'url_stuff': stuff_url,
'size': size,
'color': color,
'cloth': cloth
}
driver_new.quit()
print(data)
write_csv(data, r'D:\tmp\my_prod\Python\python\parsing_ARGO\argo.csv')
def main():
path = os.path.abspath(input('Введите путь к папке: '))
if path == '':
path = os.curdir
FileName = input('Введите путь и название файла с результатами: ')
if FileName == '':
FileName = 'ListFile.csv'
data = []
data = (os.listdir(path))
for line in data:
Data = {'Имя файла': line}
write_csv(Data, FileName)
def GetData(brand, model, img, mainUrl):
dataCsv = {'Brand': brand['nameBrand'],
'Model': model['nameModel'],
'Img Directory': brand['nameBrand']+'\\'+model['nameModel']+'\\'+img['nameImg']+'.jpg' if img['nameImg'] != None else 'None'}
if img['nameImg'] != None:
pathImg = os.path.join(
'tablets', brand['nameBrand'], model['nameModel'])
os.makedirs(pathImg)
with open(os.path.join(pathImg, img['nameImg']+'.jpg'), 'wb') as imageFile:
imageFile.write(requests.get(mainUrl+img['urlImg']).content)
imageFile.close()
write_csv(dataCsv, 'Tablet.csv')
def get_stuff_info(list_stuff_on_site):
for stuff in list_stuff_on_site:
html = get_html(stuff['stuff_url'])
with open('0.html', 'w', encoding='utf-8') as f:
f.write(html)
f.close()
soup = BeautifulSoup(html, 'lxml')
try:
descr = soup.find('div', id='tab-description').text
except AttributeError:
descr = ''
try:
atr = soup.find(
'div', id='tab-specification').find('div', class_='attribute').text
except AttributeError:
atr = ''
try:
size_span = soup.find('div', class_='option row').find(
'tbody').find_all('span', class_='size-title')
except AttributeError:
size_span = []
size_span = soup.find('div', class_='option row').find(
'tbody').find_all('span', class_='size-title')
size = []
for size_tmp in size_span:
size.append(size_tmp.text)
','.join(size)
data = {'catalog_name': stuff['catalog_name'],
'stuff_name': stuff['stuff_name'],
'stuff_url': stuff['stuff_url'],
'descr': descr.replace('\n', ' ').replace('\r', ' '),
'size': size,
'atr': atr.replace('\n', ' ').replace('\r', ' ')}
main_dir = r'D:\tmp\python\python_parsing\parsing_ck_textil'
write_csv(
data, r'D:\tmp\python\python_parsing\parsing_ck_textil\ck_textil.csv')
try:
image_tag_a_list = soup.find(
'div', class_='MagicToolboxSelectorsContainer').find_all('a')
except AttributeError:
image_tag_a_list = soup.find(
'div', class_='MagicToolboxContainer selectorsBottom minWidth').find_all('a')
image_dir = os.path.join(
main_dir, stuff['catalog_name'], stuff['stuff_name']).replace(' ', '_')
os.makedirs(image_dir)
for i, image_tmp in enumerate(image_tag_a_list):
image_tmp.get('href')
image_url = 'https://' + image_tmp.get('href')[2:]
with open(os.path.join(image_dir, '{}.jpg'.format(i)), 'wb') as file:
file.write(requests.get(image_url).content)
write_csv(data, os.path.join(image_dir, 'info.csv'))
def get_stuff_on_page(page_catalog_url):
list_stuff_on_page = []
html = get_html(page_catalog_url)
soup = BeautifulSoup(html, 'lxml')
list_stuff = soup.find_all('div', class_='product-thumb transition')
catalog_name = soup.find('h1').text
for stuff in list_stuff:
url = stuff.find('div', class_='caption').find('a').get('href')
stuff_name = stuff.find(
'div', class_='caption').find('a').text.replace('"', '')
data = {'catalog_name': catalog_name,
'stuff_name': stuff_name,
'stuff_url': url}
list_stuff_on_page.append(data)
write_csv(data, 'ck.csv')
return list_stuff_on_page
def GetListBrandAndModels(mainUrl):
html = get_html(mainUrl)
soup = BeautifulSoup(html, 'lxml')
ListBrandDiv = soup.find_all('div', class_='category-wrap')
for Div in ListBrandDiv:
BrandName = Div.find('div', class_='text').find('a').text
try:
ListModelsA = Div.find('div', class_='sub').find_all('a')
except AttributeError:
ListModelsA = ''
for A in ListModelsA:
Text = A.text
if Text != 'Показать еще':
ModelName = Text
Url = A.get('href')
data = {'Brand': BrandName, 'Model': ModelName, 'Url': Url}
write_csv(data, 'Mobi711.csv')
def get_all_stuff(list_stuff):
list_dir = []
for stuff in list_stuff:
html = get_html(stuff['stuff_url'])
soup = BeautifulSoup(html, 'lxml')
with open('0.html', 'w', encoding='utf-8') as file:
file.write(html)
file.close()
try:
descr = soup.find(
'div',
class_='block-text block-type-catalogitem-text textcontent'
).find('p').text
except:
descr = ''
try:
url_image = soup.find('div',
class_='block-picture').find('a').get('href')
except:
continue
catalog_name = stuff['catalog_name']
stuff_name = stuff['stuff_name'].replace('"', '')
stuff_url = stuff['stuff_url']
data = {
'catalog_name': catalog_name,
'stuff_name': stuff_name,
'stuff_url': stuff_url,
'stuff_descr': descr
}
main_dir = r'D:\tmp\python\python_parsing\parsing_formateks'
new_dir = os.path.join(main_dir, catalog_name,
stuff_name).replace(' ', '_').lower()
if new_dir in list_dir:
new_dir = new_dir + '_1'
else:
list_dir.append(new_dir)
os.makedirs(new_dir)
write_csv(data, os.path.join(new_dir, 'info.csv'))
write_csv(data, os.path.join(main_dir, 'formarket.csv'))
with open(os.path.join(new_dir, '0.jpg'), 'wb') as file:
file.write(requests.get(url_image).content)
file.close()
def get_stuff_on_page(url_catalog):
for item in url_catalog:
for page in range(item['max_page']):
if page == 0:
html = get_html(item['url'])
else:
html = get_html(item['url'] + '/page-{}'.format(page + 1))
soup = BeautifulSoup(html, 'lxml')
with open('0.html', 'w', encoding='utf-8') as f:
f.write(html)
f.close()
stuff_div = soup.find(
'div', class_='catalog-collection cleared').find_all('h3')
for stuff in stuff_div:
stuff_url = 'http://formateks.ru' + stuff.find('a').get('href')
stuff_name = stuff.find('a').text
data = {
'catalog_name': item['catalog_name'],
'stuff_name': stuff_name,
'stuff_url': stuff_url
}
write_csv(data, 'formarket.csv')
import os
from my_lib import write_csv
file_list = os.listdir(r'D:\Done\Antyspy')
for file in file_list:
data = {'name': file.replace('.jpg', '')}
write_csv(data, "tmp.csv")
