def telekom_internet(scraper_url: str):
soup = get_soup(scraper_url)
oferte = soup.select('.oferte-container div.oferta')
packages = []
for oferta in oferte:
price = oferta.select_one('.bottomContent h3.magenta').text
name = oferta.select_one('h2').text
detail_url = oferta.select_one('.bottomContent a')['href']
id_hint = url_last_path(detail_url, scraper_url)
characteristics = {}
for feature in oferta.select('ul li'):
feature_text = feature.text.lower()
channels = parse_metric(feature_text, ['canale'])
if channels and 'online' not in feature_text:
characteristics['tv_nchan'] = format_units(channels)
elif 'inclus' in feature_text:
characteristics['tv_rcvr'] = [True]
package = {
'name': name.strip(),
'price': format_units(price),
'scraper_id_hint': id_hint.strip(),
'characteristics': characteristics
}
packages.append(package)
return json.dumps({"packages": packages})
def telekom_internet(scraper_url: str):
soup = get_soup(scraper_url)
oferte = soup.select('.oferte-container div.oferta')
packages = []
for oferta in oferte:
price = oferta.select_one('.bottomContent h3.magenta').text
name = oferta.select_one('h2').text
detail_url = oferta.select_one('.bottomContent a')['href']
id_hint = url_last_path(detail_url, scraper_url)
characteristics = {}
for feature in oferta.select('ul li'):
feature_text = feature.text.lower()
speed = parse_metric(feature_text, ['Mbps', 'Gbps'])
if speed:
characteristics['inet_down'] = characteristics[
'inet_up'] = format_units(speed)
elif 'inclus' in feature_text:
characteristics['inet_router'] = True
package = {
'name': name.strip(),
'price': format_units(price),
'scraper_id_hint': id_hint.strip(),
'characteristics': characteristics
}
packages.append(package)
return json.dumps({"packages": packages})
def get_dy2018():
url = 'https://item.mi.com/product/6334.html'
print('开始抓取AI音箱...')
soup = get_soup(get_html(url, 'utf-8'))
# print(soup.prettify())
a = soup.select('#J_buyBtnBox a')
print(a)
def get_initial_urls():
initial_url_lists = ['https://www.tapology.com/rankings/current-top-ten-lightweight-mma-fighters-155-pounds',
'https://www.tapology.com/rankings/current-top-ten-featherweight-mma-fighters-145-pounds',
'https://www.tapology.com/rankings/current-top-ten-bantamweight-mma-fighters-135-pounds',
'https://www.tapology.com/rankings/35-top-flyweight-mma-fighters',
'https://www.tapology.com/rankings/1261-top-women-bantamweight-fighters',
'https://www.tapology.com/rankings/1262-top-women-flyweight-fighters',
'https://www.tapology.com/rankings/1263-top-women-strawweight-fighters',
'https://www.tapology.com/rankings/1264-top-women-atomweight-fighters',
'https://www.tapology.com/rankings/1265-top-women-featherweight-fighters',
'https://www.tapology.com/rankings/current-top-ten-best-pound-for-pound-mma-and-ufc-fighters',
'https://www.tapology.com/rankings/top-ten-fan-favorite-mma-and-ufc-fighters',
'https://www.tapology.com/rankings/33-current-best-pound-for-pound-female-mma-fighters',
'https://www.tapology.com/rankings/current-top-ten-heavyweight-mma-fighters-265-pounds',
'https://www.tapology.com/rankings/current-top-ten-light-heavyweight-mma-fighters-205-pounds',
'https://www.tapology.com/rankings/current-top-ten-middleweight-mma-fighters-185-pounds',
'https://www.tapology.com/rankings/current-top-ten-welterweight-mma-fighters-170-pounds'
]
output_urls = set()
for url_ranking_page_url in initial_url_lists:
soup = get_soup(url_ranking_page_url)
name_soups = soup.find_all('div', {'class':'rankingItemsItemRow name'})
next_batch_of_urls = set([parse.urljoin(base_url, i.find('a')) for i in name_soups if i.find('a')])
output_urls.update(next_batch_of_urls)
return output_urls
def kathmandu_post_extractor():
url = 'https://kathmandupost.ekantipur.com'
soup = get_soup(url)
more_news_section = soup.find('div', class_='block--morenews')
news_list = more_news_section.find_all('article', class_="article-image")
main_list = []
for news in news_list:
post_link = news.a['href']
default_link = "https://kathmandupost.ekantipur.com"
full_link = default_link + post_link
title = news.contents[1].h3.text
image_div = news.find('div', class_='image')
try:
image_link = image_div.figure.a.img['data-src']
except:
image_link = "img not available"
date_url = news.a['href']
date = get_date(date_url)
summary = news.p.text
news_dict = {
"image_link": image_link,
"title": title,
"nep_date": date,
"source": "ekantipur",
"news_link": full_link,
"summary": summary,
}
main_list.append(news_dict)
last_list = featured_news(soup) + main_list
return last_list
def orange_abon(scraper_url: str):
soup = get_soup(scraper_url)
feature_kw = OrderedDict([
('mobil_min_nat mobil_sms_nat', 'minute sms naiona'),
('mobil_min_nat', 'minute naiona'),
('mobil_sms_nat', 'sms naiona'),
('mobil_min_internat', 'minute interna'),
('mobil_date', 'trafic internet'),
])
abonamente = soup.select('.carusel-abo .item')
packages = []
for abon in abonamente:
name = abon.select_one('.minbenbox.romico h3').text
price = abon.select_one('.secbenbox .lefttext').text
features = abon.select('.minbenbox.romico .minben')
features = [(f.select_one('.descben').text.strip().lower(),
str(f.contents[0]).strip()) for f in features]
characteristics = extract_features(features, feature_kw, name)
packages.append({
'name': name.strip(),
'price': format_units(price),
'characteristics': characteristics
})
return json.dumps({"packages": packages})
def kantipur_daily_extractor():
news_list = []
url = 'https://www.kantipurdaily.com/news'
soup = get_soup(url)
for article in soup.find_all('article', class_='normal'):
title = article.h2.a.text
#author = article.find('div', class_='author').text
summary = article.find('p').text
image = article.find('div', class_="image").figure.a.img["data-src"]
img = image.replace("-lowquality", "")
small_img = img.replace("lowquality", "")
big_img = small_img.replace("300x0", "1000x0")
date_ore = article.h2.a['href']
contaminated_list = date_ore.split('/')
pure_date_list = [
contaminated_list[2], contaminated_list[3], contaminated_list[4]
]
date = "/".join(pure_date_list)
link = "https://kantipurdaily.com" + date_ore
news_dict = {
'title': title,
'nep_date': date,
'source': 'ekantipur',
'summary': summary,
'news_link': link,
'image_link': big_img,
}
news_list.append(news_dict)
return news_list
def scrape_url(url):
output = []
soup = get_soup(url)
fighter_info_soup = soup.find('div', {'class':'details details_two_columns'})
fighter_info_soup = fighter_info_soup.find('ul', recursive = False)
fighter_info_soups = fighter_info_soup.find_all('li', recursive = False)
fighter_info_dict = dict()
for i in fighter_info_soups:
label = i.find('strong').getText()
value = i.find('span').getText()
fighter_info_dict[label] = value
def extractor(category=None, section='gen'):
if not category:
category = [27] if section == 'intl' else [21, 22, 24, 25, 26, 31]
elif category:
_resolve_category(category)
all_news = []
for category_no in category:
url = f'http://nagariknews.nagariknetwork.com/category/{category_no}'
print("Resolved url", url)
soup = get_soup(url)
news_list = _soup_extractor(soup)
all_news += news_list
print(f"Length of all {len(all_news)}")
return all_news
def telekom_mobil_abonamente(scraper_url: str):
response_body = get_json(scraper_url)
products_html = response_body['productsHtml']
soup = bs4.BeautifulSoup(products_html, 'html5lib')
feature_kw = OrderedDict([('mobil_min_internat', 'min internationale'),
('mobil_min_nat', 'min nationale'),
('mobil_date', 'trafic date'),
('mobil_sms_nat', 'sms nationale')])
packages = []
abonamente = soup.select('div.abonamenteTabWrapper')
for abon in abonamente:
detail_url = abon.select_one('div.abonamenteButtons a')['href']
if not urlparse(detail_url).netloc:
detail_url = urljoin(scraper_url, detail_url)
abon_name = abon.select_one('div.abonamenteTabTitle strong').text
abon_price = abon.select_one('.abonamentePrice strong').text
abon_id = urlparse(detail_url).path
abon_id = os.path.basename(os.path.normpath(abon_id))
abon_details = get_soup(detail_url)
features = abon_details.select('#tab-1 .tarrifs-table tbody tr')
characteristics = {}
for feature in features:
feature_name, feature_value = map(_extract_p_data,
feature.select('td'))
feature_words = re.sub('[^a-z]', '', feature_name.lower())
for alias, kws in feature_kw.items():
if all(kw in feature_words for kw in kws.split(' ')):
characteristics[alias] = format_units(feature_value)
break
if not all(alias in characteristics for alias in feature_kw.keys()):
missing = set(feature_kw.keys()) - set(characteristics.keys())
# raise ScraperError(f"{abon_name} missing values for [{', '.join(missing)}]")
print(f"{abon_name} missing values for [{', '.join(missing)}]")
package = {
'name': abon_name.strip(),
'price': format_units(abon_price),
'scraper_id_hint': abon_id.strip(),
'characteristics': characteristics
}
packages.append(package)
return json.dumps({"packages": packages})
def get_dy2018():
url = 'https://www.dy2018.com/'
print('开始抓取dy2018...')
soup = get_soup(get_html(url, 'gb2312'))
# print(soup.prettify())
list = soup.select('.co_content222 li')
print("共搜索到" + str(len(list)) + "条记录")
for i in list:
one = i
a = one.select('a')[0]
a_href = a['href']
a_title = a['title']
print(base_url + a_href)
print(a_title)
print("")
from datetime import datetime
from bs4 import BeautifulSoup as BS
import requests
from common import get_soup
url = 'https://kathmandupost.ekantipur.com'
soup = get_soup(url)
def kathmandu_post_extractor():
url = 'https://kathmandupost.ekantipur.com'
soup = get_soup(url)
more_news_section = soup.find('div', class_='block--morenews')
news_list = more_news_section.find_all('article', class_="article-image")
main_list = []
for news in news_list:
post_link = news.a['href']
default_link = "https://kathmandupost.ekantipur.com"
full_link = default_link + post_link
title = news.contents[1].h3.text
image_div = news.find('div', class_='image')
try:
image_link = image_div.figure.a.img['data-src']
except:
image_link = "img not available"
date_url = news.a['href']
date = get_date(date_url)
summary = news.p.text
news_dict = {
"image_link": image_link,
