def download_page(soup, category_name=None):
product_list = soup.find('div', 'n-snippet-list').find_all('div', 'n-snippet-card2', recursive=False)
logger.debug('download_item got {} items'.format(len(product_list)))
for i in product_list:
download_item(i, category_name)
async def main(link_set):
while link_set:
url_object_form_json = link_set.pop()
logger.debug(f'url_object_form_json {str(url_object_form_json)}')
tasks.append(asyncio.create_task(download_page(url_object_form_json)))
# print(tasks)
await asyncio.gather(*tasks)
def __init__(self, soup):
self.soup = soup
self.pros = ''
self.cons = ''
self.comment = ''
# write_tmp_soup(soup)
try:
self.id = soup['data-review-id']
except KeyError:
self.id = soup.div['data-review-id']
data = self.soup.find('div', {'itemprop': 'review'})
if data:
logger.debug('Review trying NEW method...')
self.date = datetime.strptime(
data.find('meta', {'itemprop': 'datePublished'})['content'],
'%Y-%m-%d')
self.author = data.find('meta', {'itemprop': 'author'})['content']
self.description = data.find(
'meta', {'itemprop': 'description'})['content']
self.rating = data.find('div', {
'itemprop': 'reviewRating'
}).find('meta', {'itemprop': 'ratingValue'})['content']
self.parse_description()
else:
logger.debug('Review trying OLD method...')
self.date = self.process_date_string(
soup.find('span', 'n-product-review-item__date-region').string)
self.author = soup.find('', 'n-product-review-user__name').string
# self.comment = soup.find('dd', 'n-product-review-item__text').string
# self.description = f'{self.COMMENT_WORD} {self.comment}'
self.rating = soup.find('div', 'rating__value').string
self.process_description_from_markup()
def session(self):
if self.__session__:
return self.__session__
print(self.model.__tablename__, ' session init')
logger.debug(f'{self.__class__} session init')
self.recreate_session()
return self.__session__
def get_reviews_all(self):
logger.debug('ReviewList::getting data from page 1')
self.get_reviews_from_page(self.soup)
for page_num in range(2, self.pages + 1):
new_url = '{}&{}'.format(self.url, PAGE_PARAM.format(page_num))
logger.debug(
'ReviewList::getting data from page {}'.format(page_num))
soup = get_soup(new_url)
self.get_reviews_from_page(soup)
async def download_link(soup, category_name=None):
session = Session()
product_list = soup.find('div',
'n-snippet-list').find_all('div',
'n-snippet-card2',
recursive=False)
logger.debug('download_link got {} items'.format(len(product_list)))
tasks = []
for i in product_list:
tasks.append(
asyncio.create_task(
download_item(session=session,
product_soup=i,
category_name=category_name)))
print('LOOP END')
await asyncio.gather(*tasks)
def download_list_all(url_object):
category_name, url = url_object.get('category_name'), url_object['url']
soup = get_soup(url)
pages_count = get_pages_count(soup)
logger.debug(f'Found {pages_count} pages for list url {url}')
logger.debug('download_list::getting data from page 1')
download_page(soup, category_name)
for page_num in range(2, pages_count + 1):
logger.debug(f'download_list::getting data from page {page_num}')
new_url = '{}&{}'.format(url, PAGE_PARAM.format(page_num))
soup = get_soup(new_url)
download_page(soup, category_name)
async def download_page(url_object):
category_name, url = url_object.get('category_name'), url_object['url']
# try: #todo: remove all tries like that
soup = await get_soup(url)
# if not soup:
# logger.error(f'{category_name}, {url}')
# raise TypeError
# except (ConnectionError, TimeoutError):
# logger.critical(f'Some shit happened to url: {url} :: 64')
# return
pages_count = get_pages_count(soup)
logger.debug(f'Found {pages_count} pages for list url {url}')
logger.debug('download_page::getting data from page 1')
tasks = [asyncio.create_task(download_link(soup, category_name))]
for page_num in range(2, pages_count + 1):
logger.debug(f'download_list::getting data from page {page_num}')
new_url = '{}&{}'.format(url, PAGE_PARAM.format(page_num))
soup = await get_soup(new_url)
tasks.append(asyncio.create_task(download_link(soup, category_name)))
await asyncio.gather(*tasks)
download_item(i, category_name)
def download_list_all(url_object):
category_name, url = url_object.get('category_name'), url_object['url']
soup = get_soup(url)
pages_count = get_pages_count(soup)
logger.debug(f'Found {pages_count} pages for list url {url}')
logger.debug('download_list::getting data from page 1')
download_page(soup, category_name)
for page_num in range(2, pages_count + 1):
logger.debug(f'download_list::getting data from page {page_num}')
new_url = '{}&{}'.format(url, PAGE_PARAM.format(page_num))
soup = get_soup(new_url)
download_page(soup, category_name)
if __name__ == '__main__':
link_set = get_link_set()
# link_set = json.load(open(LINK_SET_PATH, 'r', encoding='utf8'))
logger.info('START\n')
# random.shuffle(link_set)
DOWNLOAD_IMAGES = input('DOWNLOAD_IMAGESs? (Y/N)\n').lower() == 'y'
RESOLVE_OTHER_SHOP_URL = input('RESOLVE_OTHER_SHOP_URL? (Y/N)\n').lower() == 'y'
while link_set:
url_object_form_json = link_set.pop()
logger.debug(f'url_object_form_json {str(url_object_form_json)}')
download_list_all(url_object_form_json)
def __init__(self, url):
self.url = url
self.soup = get_soup(url)
self.pages = get_pages_count(self.soup)
logger.debug('Review pages found: {}'.format(self.pages))
self.get_reviews_all()
def get_reviews_from_page(self, soup):
review_items = soup.find_all('div', 'n-product-review-item')
logger.debug('ReviewList got {} items'.format(len(review_items)))
for i in review_items:
self.append(Review(i))
