def crawler_news(self):
response = crawler.MakeRequest(self.url,
'Post',
postData=self.body,
headers=self.headers)
news_json = json.loads(response.content.decode('utf-8'))
if news_json:
soup = BeautifulSoup(news_json['data'], 'html.parser')
bulk_obj = DbOperations.Get_object_for_bulkop(
False, 'shinetsu_news')
news_data = soup.find_all('div', {'class': "item"})
if news_data:
for news in news_data:
news_dict = Helper.get_news_dict()
title_data = news.find('div', {'class': 'title'})
title = title_data.text.strip().split(
'\n')[0] if title_data else ""
url_data = news.find('a', {'href': True})
url = url_data['href'] if url_data else ''
publish_date_data = news.find('p', {'class': 'date'})
publish_date = Helper.parse_date(
publish_date_data.text
) if publish_date_data and publish_date_data.text != '' else ''
if url.split('.')[-1] != 'pdf':
url_response = crawler.MakeRequest(
url,
'Get',
postData=self.body,
headers=self.headers)
url_soup = BeautifulSoup(url_response.content,
'html.parser')
description_data = url_soup.find(
'div', {'class': "content-news"})
description = []
regex = re.compile(r'[\n\xa0]')
for desc in description_data.find_all('p'):
description.append(regex.sub("", str(desc.text)))
description = ''.join(description)
else:
description = ''
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"url":
url,
"link":
url,
"news_url_uid":
hashlib.md5(url.encode()).hexdigest(),
"description":
description,
"text":
description,
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"shinetsu",
"ticker":
"shinetsu_scrapped",
"industry_name":
"shinetsu",
"news_provider":
"shinetsu"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, 'shinetsu_news')
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 0:
bulk_obj.execute()
else:
print("News Not Found")
def crawler_news(self):
try:
response = crawler.MakeRequest(self.url,
'Get',
postData=self.body,
headers=self.headers)
soup = BeautifulSoup(response.content, 'html.parser')
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
news_data = soup.find('div', {'id': "newsRelease"})
if news_data:
for news in news_data.find_all(
'div', {'class': 'grid-sizer grid-item news--item'}):
news_dict = Helper.get_news_dict()
title_data = news.find('h4')
title = title_data.text if title_data else ""
url_data = news.find('a', {'href': True})
url = "https://global.canon/" + str(
url_data['href']) if url_data else ''
# Check if already present
unqUrl = hashlib.md5(url.encode()).hexdigest()
chkIsExists = DbOperations.GetData(
self.news_collection, {"news_url_uid": str(unqUrl)},
{}, QueryType.one)
if (chkIsExists):
print("Already saved. url - ( " + url + " )")
continue
publish_date_data = news.find('div',
{'class': 'news-date'})
publish_date = Helper.parse_date(
publish_date_data.text
) if publish_date_data and publish_date_data.text != '' else ''
url_response = crawler.MakeRequest(url,
'Get',
postData=self.body,
headers=self.headers)
url_soup = BeautifulSoup(url_response.content,
'html.parser')
description_data = url_soup.find('div', {
'id': 'news-detail'
}).find_all('div', {'class': "col-row"})[1]
description = []
regex = re.compile(r'[\n\xa0]')
for desc in description_data.find_all('p'):
description.append(regex.sub("", str(desc.text)))
description = ''.join(description)
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"url":
url,
"link":
url,
"news_url_uid":
hashlib.md5(url.encode()).hexdigest(),
"description":
description,
"text":
description,
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"canon",
"ticker":
"canon_scrapped",
"industry_name":
"canon",
"news_provider":
"canon"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 0:
bulk_obj.execute()
else:
print("All news has been scrapped !!")
loop = False
except Exception as e:
self.logger.error(f"Error Occured : \n", exc_info=True)
def crawler_news(self):
response = crawler.MakeRequest(self.url,
'Get',
postData=self.body,
headers=self.headers)
soup = BeautifulSoup(response.content, 'html.parser')
bulk_obj = DbOperations.Get_object_for_bulkop(False, 'arrow_news')
news_data = json.loads(response.content.decode('utf-8'))
if news_data:
for news in news_data['GetPressReleaseListResult']:
news_dict = Helper.get_news_dict()
title = news['Headline'] if 'Headline' in news else ""
url = "https://news.fiveyearsout.com" + str(
news['LinkToDetailPage']
) if 'LinkToDetailPage' in news else ''
publish_date = Helper.parse_date(
news['PressReleaseDate']
) if 'PressReleaseDate' in news else ''
url_response = crawler.MakeRequest(url,
'Get',
postData=self.body,
headers=self.headers)
url_soup = BeautifulSoup(url_response.content, 'html.parser')
description_data = url_soup.find('div',
{'class': "module_body"})
description = []
regex = re.compile(r'[\n\xa0]')
for desc in description_data.find_all('p'):
description.append(regex.sub("", str(desc.text)))
description = ''.join(description)
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"url":
url,
"link":
url,
"news_url_uid":
hashlib.md5(url.encode()).hexdigest(),
"description":
description,
"text":
description,
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"arrow",
"ticker":
"arrow_scrapped",
"industry_name":
"arrow",
"news_provider":
"arrow"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, 'arrow_news')
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']) > 0:
bulk_obj.execute()
else:
print("News Not Found")
def crawler_news(self):
try:
loop = True
page = 1
while loop:
response = crawler.MakeRequest(self.url.format(page=page),
'Get',
postData=self.body,
headers=self.headers)
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
news_data = json.loads(response.content.decode('utf-8'))
if news_data:
for news in news_data:
news_dict = Helper.get_news_dict()
title = news['title'][
'rendered'] if 'title' in news and 'rendered' in news[
'title'] else ''
url = news['link'] if 'link' in news else ''
# Check if already present
unqUrl = hashlib.md5(url.encode()).hexdigest()
chkIsExists = DbOperations.GetData(
self.news_collection,
{"news_url_uid": str(unqUrl)}, {}, QueryType.one)
if (chkIsExists):
print("Already saved. url - ( " + url + " )")
continue
publish_date_data = news[
'date_gmt'] if 'date_gmt' in news else ''
publish_date = Helper.parse_date(publish_date_data)
description_data = BeautifulSoup(
news['acf']['sections'][0]['text'], 'html.parser')
description = []
regex = re.compile(r'[\n\xa0]')
for desc in description_data.find_all('p'):
description.append(regex.sub("", str(desc.text)))
description = ''.join(description)
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"url":
url,
"link":
url,
"news_url_uid":
hashlib.md5(url.encode()).hexdigest(),
"description":
description,
"text":
description,
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"tereos",
"ticker":
"tereos_scrapped",
"industry_name":
"tereos",
"news_provider":
"tereos"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.
__dict__['ops']) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 0:
bulk_obj.execute()
page += 1
else:
print("All news has been scrapped !!")
loop = False
except Exception as e:
self.logger.error(f"Error Occured : \n", exc_info=True)
def crawler_news(self):
try:
loop = True
page = 1
while loop:
response = crawler.MakeRequest(self.url.format(page=page),
'Get',
postData=self.body,
headers=self.headers)
if (response.status_code == 200):
soup = BeautifulSoup(response.content, 'html.parser')
else:
break
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
news_data = soup.find('div', {
'class': "x-main full"
}).find_all('div', {'class': 'x-container max width'})
if news_data:
for news in news_data:
news_dict = Helper.get_news_dict()
title_data = news.find('h2', {'class': 'entry-title'})
title = title_data.text.strip() if title_data else ""
url_data = news.find('a', {'href': True})
url = url_data['href'] if url_data else ''
# Check if already present
unqUrl = hashlib.md5(url.encode()).hexdigest()
chkIsExists = DbOperations.GetData(
self.news_collection,
{"news_url_uid": str(unqUrl)}, {}, QueryType.one)
if (chkIsExists):
print("Already saved. url - ( " + url + " )")
continue
publish_date_data = news.find('time',
{'class': 'entry-date'})
publish_date = Helper.parse_date(
publish_date_data.text
) if publish_date_data and publish_date_data.text != '' else ''
url_response = crawler.MakeRequest(
url,
'Get',
postData=self.body,
headers=self.headers)
url_soup = BeautifulSoup(url_response.content,
'html.parser')
description_data = url_soup.find(
'div', {'class': "entry-content content"})
description = []
regex = re.compile(r'[\n\xa0]')
if description_data.h2 != None:
for desc in description_data.h2.find_all_previous(
"p")[::-1]:
description.append(
regex.sub("", str(desc.text)))
else:
for desc in description_data.find_all('p'):
description.append(
regex.sub("", str(desc.text)))
description = ''.join(description)
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"url":
url,
"link":
url,
"news_url_uid":
hashlib.md5(url.encode()).hexdigest(),
"description":
description,
"text":
description,
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"titanx",
"ticker":
"titanx_scrapped",
"industry_name":
"titanx",
"news_provider":
"titanx"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.
__dict__['ops']) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 0:
bulk_obj.execute()
page += 1
else:
print("All news has been scrapped !!")
loop = False
except Exception as e:
self.logger.error(f"Error Occured : \n", exc_info=True)
def crawler_news(self):
response = crawler.MakeRequest(self.url,
'Get',
postData=self.body,
headers=self.headers)
bulk_obj = DbOperations.Get_object_for_bulkop(False,
'asahi_kasei_news')
news_data = json.loads(response.content.decode('utf-8'))
if news_data:
for news_list in news_data[0]['2020'][1]['release'][0]['mooth']:
for news in news_list['item']:
news_dict = Helper.get_news_dict()
title = news['text'] if 'text' in news else ''
url = "https://www.asahi-kasei.com" + str(
news['url']) if 'url' in news else ''
publish_date_data = news['day'] if 'day' in news else ''
publish_date = Helper.parse_date(publish_date_data)
url_response = crawler.MakeRequest(url,
'Get',
postData=self.body,
headers=self.headers)
url_soup = BeautifulSoup(url_response.content,
'html.parser')
description_data = url_soup.find('main', {'class': "main"})
description = []
regex = re.compile(r'[\n\xa0]')
for desc in description_data.find_all('p'):
description.append(regex.sub("", str(desc.text)))
description = ''.join(description)
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"url":
url,
"link":
url,
"news_url_uid":
hashlib.md5(url.encode()).hexdigest(),
"description":
description,
"text":
description,
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"asahi_kasei",
"ticker":
"asahi_kasei_scrapped",
"industry_name":
"asahi_kasei",
"news_provider":
"asahi_kasei"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, 'asahi_kasei_news')
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 0:
bulk_obj.execute()
else:
print("News Not Found")
def crawler_news(self):
loop = True
page = 0
while loop:
response = crawler.MakeRequest(self.url.format(page=page),
'Get',
postData=self.body,
headers=self.headers)
soup = BeautifulSoup(response.content, 'html.parser')
bulk_obj = DbOperations.Get_object_for_bulkop(
False, 'aruplab_news')
news_data = soup.find_all('div', {'class': "views-col"})
if news_data:
for news in news_data:
news_dict = Helper.get_news_dict()
title_data = news.find('h4')
title = title_data.text if title_data else ""
url_data = news.find('a', {'href': True})
url = "https://www.aruplab.com" + str(
url_data['href']) if url_data else ''
publish_date_data = news.find(
'span',
{'class': 'views-field views-field-field-date'})
publish_date = Helper.parse_date(
publish_date_data.text
) if publish_date_data and publish_date_data.text != '' else ''
url_response = crawler.MakeRequest(url,
'Get',
postData=self.body,
headers=self.headers)
url_soup = BeautifulSoup(url_response.content,
'html.parser')
description_data = url_soup.find('main', {
'role': "main"
}).find(
'div', {
'class':
'field field--name-body field--type-text-with-summary field--label-hidden field__item'
})
description = []
regex = re.compile(r'[\n\xa0]')
for desc in description_data.find_all('p'):
description.append(regex.sub("", str(desc.text)))
description = ''.join(description)
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"url":
url,
"link":
url,
"news_url_uid":
hashlib.md5(url.encode()).hexdigest(),
"description":
description,
"text":
description,
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"aruplab",
"ticker":
"aruplab_scrapped",
"industry_name":
"aruplab",
"news_provider":
"aruplab"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, 'aruplab_news')
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 0:
bulk_obj.execute()
page += 1
else:
print("News Not Found")
loop = False
def crawler_news(self):
"""
This function will scrap news page wise for given url
:return:
"""
try:
loop = True
page = 0
while loop:
response = crawler.MakeRequest(self.url.format(page=page),
'Get',
postData=self.body,
headers=self.headers)
soup = BeautifulSoup(response.content, 'html.parser')
bulk_obj = DbOperations.Get_object_for_bulkop(
False, 'harvardbioscience_news')
news_data = soup.find('tbody')
if news_data:
for news in news_data.find_all('tr'):
try:
news_dict = Helper.get_news_dict()
title_data = news.find(
'td', {
'class':
'views-field views-field-field-nir-news-title'
}).find('a', {'href': True})
title = title_data.text.strip(
) if title_data else ""
url_data = news.find(
'td', {
'class':
'views-field views-field-field-nir-news-title'
}).find('a', {'href': True})
url = "https://investor.harvardbioscience.com" + str(
url_data['href']) if url_data else ''
publish_date_data = news.find(
'time', {'class': 'datetime'})
publish_date = Helper.parse_date(
publish_date_data.text
) if publish_date_data else ''
url_response = crawler.MakeRequest(
url,
'Get',
postData=self.body,
headers=self.headers)
url_soup = BeautifulSoup(url_response.content,
'html.parser')
description_data = url_soup.find(
'div', {'class': 'node__content'})
description = []
regex = re.compile(r'[\n\xa0]')
for desc in description_data.find_all('p'):
description.append(
regex.sub("", str(desc.text)))
description = ''.join(description)
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"url":
url,
"link":
url,
"news_url_uid":
hashlib.md5(url.encode()).hexdigest(),
"description":
description,
"text":
description,
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"harvardbioscience",
"ticker":
"harvardbioscience_scrapped",
"industry_name":
"harvardbioscience",
"news_provider":
"harvardbioscience"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.
__dict__['ops']) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, 'harvardbioscience_news')
except Exception as e:
self.logger.error(f"Error Occured : \n",
exc_info=True)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 0:
bulk_obj.execute()
page += 1
else:
print("News Not Found")
loop = False
except Exception as e:
self.logger.error(f"Error Occured : \n", exc_info=True)
def crawler_news(self):
try:
response = crawler.MakeRequest(self.url,
'Get',
postData=self.body,
headers=self.headers)
soup = BeautifulSoup(response.content, 'html.parser')
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
news_data = soup.find_all(
'div', class_='small-12 columns event-post-info')
if news_data:
for news in news_data:
news_dict = Helper.get_news_dict()
title_data = news.find('h6')
title = title_data.text if title_data else ""
url_data = news.find('a', {'href': True})
url = str(url_data['href']) if url_data else ''
# Check if already present
unqUrl = hashlib.md5(url.encode()).hexdigest()
chkIsExists = DbOperations.GetData(
self.news_collection, {"news_url_uid": str(unqUrl)},
{}, QueryType.one)
if (chkIsExists):
print("Already saved. url - ( " + url + " )")
continue
publish_date_data = news.find('span', class_='date caps')
publish_date = Helper.parse_date(
publish_date_data.text
) if publish_date_data and publish_date_data.text != '' else ''
url_response = crawler.MakeRequest(url,
'Get',
postData=self.body,
headers=self.headers)
url_soup = BeautifulSoup(url_response.content,
'html.parser')
description_data = url_soup.find('div', {'class': ""})
description = []
regex = re.compile(r'[\n\xa0]')
for string in description_data.stripped_strings:
description.append(regex.sub("", str(string.strip())))
description = ''.join(description)
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"url":
url,
"link":
url,
"news_url_uid":
hashlib.md5(url.encode()).hexdigest(),
"description":
description,
"text":
description,
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"alertlogic",
"topic_name":
"press-releases",
"ticker":
"alertlogic_scrapped",
"industry_name":
"alertlogic",
"news_provider":
"alertlogic"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 0:
bulk_obj.execute()
else:
print("All news has been scrapped !!")
except Exception as e:
self.logger.error(f"Error Occured : \n", exc_info=True)
def crawler_news(self):
response = crawler.MakeRequest(self.url,
'Get',
postData=self.body,
headers=self.headers)
soup = BeautifulSoup(response.content, 'html.parser')
bulk_obj = DbOperations.Get_object_for_bulkop(False,
'voestalpine_news')
article_data = soup.find_all('div', {'class': 'article'})
if article_data:
for article in article_data:
news_data = article.find_all('section', {'class': ""})
for news in news_data[1::2]:
news_dict = Helper.get_news_dict()
title_data = news.find('h2')
title = title_data.text if title_data else ""
url = news.find_next_sibling(
).a['href'] if news.find_next_sibling() else ''
description_data = news.find('p')
description = description_data.text if description_data else ''
url_response = crawler.MakeRequest(url,
'Get',
postData=self.body,
headers=self.headers)
url_soup = BeautifulSoup(url_response.content,
'html.parser')
publish_date_data = url_soup.find(
'p', {'class': 'meta large inline'})
publish_date = Helper.parse_date(
publish_date_data.text.replace('|', "").strip()
) if publish_date_data and publish_date_data.text != '' else ''
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"url":
url,
"link":
url,
"news_url_uid":
hashlib.md5(url.encode()).hexdigest(),
"description":
description,
"text":
description,
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"voestalpine",
"ticker":
"voestalpine_scrapped",
"industry_name":
"voestalpine",
"news_provider":
"voestalpine"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, 'voestalpine_news')
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 0:
bulk_obj.execute()
def crawler_news(self):
try:
loop = True
page = 1
while loop:
response = crawler.MakeRequest(self.url.format(page=page),
'Get',
postData=self.body,
headers=self.headers)
soup = BeautifulSoup(response.content, 'html.parser')
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
news_data = soup.find('div', {'class': 'block-region-results'})
if news_data:
for news in news_data.find_all('tr'):
news_dict = Helper.get_news_dict()
title_data = news.find('h3')
title = title_data.text if title_data else ""
url_data = news.find('a', {'href': True})
url = "https://www.polyone.com/" + str(
url_data['href']) if url_data else ''
# Check if already present
unqUrl = hashlib.md5(url.encode()).hexdigest()
chkIsExists = DbOperations.GetData(
self.news_collection,
{"news_url_uid": str(unqUrl)}, {}, QueryType.one)
if (chkIsExists):
print("Already saved. url - ( " + url + " )")
continue
publish_date_data = news.find('h5',
{'class': 'float-left'})
publish_date = Helper.parse_date(
str(publish_date_data.text).split('\n')[0]
) if publish_date_data and publish_date_data.text != '' else ''
url_response = crawler.MakeRequest(
url,
'Get',
postData=self.body,
headers=self.headers)
url_soup = BeautifulSoup(url_response.content,
'html.parser')
description_data = url_soup.find(
'div', {'class': "block-region-top"})
description_data = description_data.strong.find_all_previous(
'p')[1:-3]
description_data.reverse()
description = []
regex = re.compile(r'[\n\xa0]')
for desc in description_data:
description.append(regex.sub("", str(desc.text)))
description = ''.join(description)
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"url":
url,
"link":
url,
"news_url_uid":
hashlib.md5(url.encode()).hexdigest(),
"description":
description,
"text":
description,
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"polyone",
"ticker":
"polyone_scrapped",
"industry_name":
"polyone",
"news_provider":
"polyone"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.
__dict__['ops']) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 0:
bulk_obj.execute()
page += 1
break
else:
print("All news has been scrapped !!")
loop = False
except Exception as e:
self.logger.error(f"Error Occured : \n", exc_info=True)
def crawler_news(self):
try:
loop = True
page = 1
while loop:
response = crawler.MakeRequest(self.url.format(page=page),
'Get',
postData=self.body,
headers=self.headers)
if response.headers[
'Content-Type'] == 'application/json; charset=utf-8':
response_json = json.loads(
response.content.decode('utf-8'))
else:
print("No data found")
break
soup = BeautifulSoup(response_json['html'], 'html.parser')
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
news_data = soup.find_all(
'li', {
'class':
'page-list--item is-detailed infinite-nodes--list-item'
})
if news_data:
for news in news_data:
news_dict = Helper.get_news_dict()
title_data = news.find('h3')
title = title_data.text.strip() if title_data else ""
url_data = news.find('a', {'href': True})
url = url_data['href'] if url_data else ''
# Check if already present
unqUrl = hashlib.md5(url.encode()).hexdigest()
chkIsExists = DbOperations.GetData(
self.news_collection,
{"news_url_uid": str(unqUrl)}, {}, QueryType.one)
if (chkIsExists):
print("Already saved. url - ( " + url + " )")
continue
publish_date_data = news.find('div',
{'class': 'meta--item'})
publish_date = Helper.parse_date(
publish_date_data.text
) if publish_date_data and publish_date_data.text != '' else ''
description_data = news.find(
'div', {'class': "page-list--text"})
description = description_data.text.strip(
) if description_data else ''
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"url":
url,
"link":
url,
"news_url_uid":
hashlib.md5(url.encode()).hexdigest(),
"description":
description,
"text":
description,
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"audi",
"ticker":
"audi_scrapped",
"industry_name":
"audi",
"news_provider":
"audi"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.
__dict__['ops']) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 0:
bulk_obj.execute()
page += 1
else:
print("All news has been scrapped !!")
loop = False
except Exception as e:
self.logger.error(f"Error Occured : \n", exc_info=True)
def crawler_news(self):
"""
This function will scrap news page wise for given url
:return:
"""
try:
loop = True
page = 1
while loop:
response = crawler.MakeRequest(self.url.format(page=page),
'Get',
postData=self.body)
soup = BeautifulSoup(response.content, 'html.parser')
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
news_list = soup.find('div', {'class': 'NewsList'})
if news_list:
news_data = news_list.find_all('li')
if news_data:
for news in news_data:
news_dict = Helper.get_news_dict()
title_data = news.find('div', {'class': 'title'})
title = title_data.text if title_data else ""
url_data = news.find('a', {'href': True})
url = "https://www.xinyiglass.com/" + str(
url_data['href']) if url_data else ''
# Check if already present
unqUrl = hashlib.md5(url.encode()).hexdigest()
chkIsExists = DbOperations.GetData(
self.news_collection,
{"news_url_uid": str(unqUrl)}, {},
QueryType.one)
if (chkIsExists):
print("Already saved. url - ( " + url + " )")
continue
regex = re.compile(r'[\n\r\t]')
description_data = news.find(
'div', {'class': 'info'})
description = regex.sub(
"", description_data.text
) if description_data else ''
date = news.find('span')
year_month = news.find('em')
publish_date = Helper.parse_date(
(year_month.text) + "-" +
str(date.text)) if date and year_month else ''
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"url":
url,
"link":
url,
"news_url_uid":
hashlib.md5(url.encode()).hexdigest(),
"description":
description.strip(),
"text":
description.strip(),
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"xinyiglass",
"ticker":
"xinyiglass_scrapped",
"industry_name":
"xinyiglass",
"news_provider":
"xinyiglass"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.
__dict__['ops']) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
if len(bulk_obj._BulkOperationBuilder__bulk.
__dict__['ops']) > 0:
bulk_obj.execute()
page += 1
else:
print("All news has been scrapped !!")
loop = False
else:
print("All news has been scrapped !!")
loop = False
except Exception as e:
self.logger.error(f"Error Occured : \n", exc_info=True)
def crawler_news(self):
loop = True
page = 0
while loop:
response = crawler.MakeRequest(
self.url,
'Post',
postData=self.body.format(page=page),
headers=self.headers)
bulk_obj = DbOperations.Get_object_for_bulkop(
False, 'novozymes_news')
news_data = json.loads(response.content.decode('utf-8'))
if news_data['News']:
for news in news_data['News']:
news_dict = Helper.get_news_dict()
title = news['Title'] if 'Title' in news else ''
url = "https://www.novozymes.com" + str(
news['Url']) if 'Url' in news else ''
publish_date_data = news[
'CreationDate'] if 'CreationDate' in news else ''
publish_date = Helper.parse_date(publish_date_data)
description = news['Content'] if 'Content' in news else ''
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"url":
url,
"link":
url,
"news_url_uid":
hashlib.md5(url.encode()).hexdigest(),
"description":
description,
"text":
description,
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"novozymes",
"ticker":
"novozymes_scrapped",
"industry_name":
"novozymes",
"news_provider":
"novozymes"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, 'novozymes_news')
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 0:
bulk_obj.execute()
page += 1
else:
print("News Not Found")
loop = False
def crawler_news(self):
loop = True
page = 1
while loop:
response = crawler.MakeRequest(self.url.format(page=page),
'Get',
postData=self.body,
headers=self.headers)
soup = BeautifulSoup(response.content, 'html.parser')
bulk_obj = DbOperations.Get_object_for_bulkop(
False, 'hanwhacorp_news')
news_data = soup.find('tbody')
if news_data and news_data.tr.text.strip() != 'There is no data.':
for news in news_data.find_all('tr'):
news_dict = Helper.get_news_dict()
title_data = news.find('td', {'class': 'title'})
title = title_data.text if title_data else ""
publish_date_data = news.find_all('td')[3].text
publish_date = Helper.parse_date(
publish_date_data
) if publish_date_data and publish_date_data != '' else ''
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"hanwhacorp",
"ticker":
"hanwhacorp_scrapped",
"industry_name":
"hanwhacorp",
"news_provider":
"hanwhacorp"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, 'hanwhacorp_news')
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 0:
bulk_obj.execute()
page += 1
else:
print("News Not Found")
loop = False
def crawler_news(self):
loop = True
page = 1
while loop:
response = crawler.MakeRequest(self.url.format(page=page),
'Get',
postData=self.body,
headers=self.headers)
soup = BeautifulSoup(response.content, 'html.parser')
bulk_obj = DbOperations.Get_object_for_bulkop(
False, 'zscaler_news')
news_data = soup.find_all(
'div', {'class': "col-12 col-md-6 zpb-32 zpb-md-48"})
if news_data:
for news in news_data:
news_dict = Helper.get_news_dict()
title_data = news.find('a')
title = title_data.text if title_data else ""
url_data = news.find('a', {'href': True})
url = url_data['href'] if url_data else ''
publish_date_data = news.find(
'time', {'class': 'text-center bg-sea-green'})
publish_date = Helper.parse_date(
publish_date_data.text
) if publish_date_data and publish_date_data.text != '' else ''
url_response = crawler.MakeRequest(url,
'Get',
postData=self.body,
headers=self.headers)
url_soup = BeautifulSoup(url_response.content,
'html.parser')
description_data = url_soup.find_all(
'div', {'class': "col-sm-12"})
description = []
regex = re.compile(r'[\n\xa0]')
for desc in description_data:
if desc.find('a', {'href': 'https://www.zscaler.com/'
}) != None:
description.append(regex.sub("", str(desc.text)))
description = ''.join(description)
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"url":
url,
"link":
url,
"news_url_uid":
hashlib.md5(url.encode()).hexdigest(),
"description":
description,
"text":
description,
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"zscaler",
"ticker":
"zscaler_scrapped",
"industry_name":
"zscaler",
"news_provider":
"zscaler"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, 'zscaler_news')
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 0:
bulk_obj.execute()
page += 1
else:
print("News Not Found")
loop = False
def crawler_news(self):
"""
This function will scrap news page wise for given url
:return:
"""
try:
response = crawler.MakeRequest(self.url,
'Get',
postData=self.body,
headers=self.headers)
soup = BeautifulSoup(response.content, 'html.parser')
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
news_data = soup.find_all('li', {'class': "NewsPanel__item"})
if news_data:
for news in news_data:
try:
news_dict = Helper.get_news_dict()
title_data = news.find('div',
{'class': 'NewsPanel__body'})
title = title_data.text.strip() if title_data else ""
url_data = news.find('a', {'href': True})
url = "https://www.kaneka.co.jp/" + str(
url_data['href']) if url_data else ''
# Check if already present
unqUrl = hashlib.md5(url.encode()).hexdigest()
chkIsExists = DbOperations.GetData(
self.news_collection,
{"news_url_uid": str(unqUrl)}, {}, QueryType.one)
if (chkIsExists):
print("Already saved. url - ( " + url + " )")
continue
publish_date_data = news.find(
'time', {'class': 'NewsPanel__time'})
publish_date = Helper.parse_date(
publish_date_data.text
) if publish_date_data else ''
url_response = crawler.MakeRequest(
url,
'Get',
postData=self.body,
headers=self.headers)
url_soup = BeautifulSoup(url_response.content,
'html.parser')
description_data = url_soup.find(
'article', {'class': 'articleBody topics__mod'})
description = []
regex = re.compile(r'[\n\xa0]')
for desc in description_data.find_all('p'):
description.append(regex.sub("", str(desc.text)))
description = ''.join(description)
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"url":
url,
"link":
url,
"news_url_uid":
hashlib.md5(url.encode()).hexdigest(),
"description":
description,
"text":
description,
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"kaneka",
"ticker":
"kaneka_scrapped",
"industry_name":
"kaneka",
"news_provider":
"kaneka"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.
__dict__['ops']) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
except Exception as e:
self.logger.error(f"Error Occured : \n", exc_info=True)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 0:
bulk_obj.execute()
else:
print("All news has been scrapped !!")
except Exception as e:
self.logger.error(f"Error Occured : \n", exc_info=True)
def crawler_news(self):
loop = True
page = 1
while loop:
response = crawler.MakeRequest(self.url.format(page=page),
'Get',
postData=self.body)
soup = BeautifulSoup(response.content, 'html.parser')
bulk_obj = DbOperations.Get_object_for_bulkop(False, 'jnj_news')
news_data = soup.find_all('div', {'class': "MediaPromo-title"})
if news_data:
for news in news_data:
news_dict = Helper.get_news_dict()
title_data = news.find('div',
{'class', 'ResponsiveText-text'})
title = title_data.text if title_data else ""
url_data = news.find('a', {'href': True})
url = url_data['href'] if url_data else ''
url_response = crawler.MakeRequest(url, 'Get')
url_soup_obj = BeautifulSoup(url_response.content,
'html.parser')
url_response_data = url_soup_obj.find(
'script', {'type': 'application/ld+json'})
url_response_data = json.loads(url_response_data.text)
if url_response_data:
publish_date = Helper.parse_date(
url_response_data['datePublished']
) if 'datePublished' in url_response_data else ''
news_provider = url_response_data['publisher'][
'name'] if 'publisher' in url_response_data and 'name' in url_response_data[
'publisher'] else ''
industry_name = news_provider
news_dict.update({
"news_provider": news_provider,
"industry_name": industry_name,
"publishedAt": publish_date,
'date': publish_date
})
description_data = url_soup_obj.find(
'div', {'class': 'FullBleedLede-dek'})
description = description_data.text if description_data else ''
news_dict.update({
"title": title,
"url": url,
"formatted_sub_header": title,
"description": description,
"link": url
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, 'jnj_well_news')
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 0:
bulk_obj.execute()
page += 1
else:
print("News Not Found")
loop = False
def crawler_news(self):
response = crawler.MakeRequest(self.url,
'Get',
postData=self.body,
headers=self.headers)
soup = BeautifulSoup(response.content, 'html.parser')
bulk_obj = DbOperations.Get_object_for_bulkop(False, 'denso_news')
news_data_1 = soup.find_all(
'div', {
'class':
"menuBlock01--border menuBlock01--small menuBlock01 menuBlock01--right"
})
news_data_2 = soup.find_all(
'div',
{'class': "menuBlock01--border menuBlock01--small menuBlock01 "})
news_data = news_data_1 + news_data_2
if news_data:
for news in news_data:
news_dict = Helper.get_news_dict()
title_data = news.find('span',
{"class": "menuBlock01__headingText"})
title = title_data.text.strip() if title_data else ""
url_data = news.find('a', {'href': True})
url = "https://www.denso.com" + str(
url_data['href']) if url_data else ''
url_response = crawler.MakeRequest(url,
'Get',
postData=self.body,
headers=self.headers)
url_response_soup = BeautifulSoup(url_response.content,
'html.parser')
description_data = url_response_soup.find(
'span', {'class': 'heading01__copy heading01__copy--lead'})
description = description_data.text.strip(
) if description_data else ''
publish_date_data = news.find('p',
{"class": "menuBlock01__text"})
publish_date_data.span.decompose()
publish_date = Helper.parse_date(
publish_date_data.text
) if publish_date_data and publish_date_data.text != '' else ''
news_dict.update({
"title": title,
"url": url,
"formatted_sub_header": title,
"description": description,
"link": url,
"publishedAt": publish_date,
'date': publish_date,
"news_provider": "denso"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, 'denso_news')
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']) > 0:
bulk_obj.execute()
def crawler_news(self):
response = crawler.MakeRequest(self.url,
'Get',
postData=self.body,
headers=self.headers)
soup = BeautifulSoup(response.content, 'html.parser')
bulk_obj = DbOperations.Get_object_for_bulkop(False,
'fujielectric_news')
news_data = soup.find('div', {'id': 'tab_news_release'})
if news_data:
for news in news_data.find_all('dt'):
news_dict = Helper.get_news_dict()
title_data = news.find_next_sibling().find_next_sibling().a
title = title_data.text if title_data else ""
url_data = news.find_next_sibling().find_next_sibling().a
url = url_data['href'] if url_data else ''
publish_date_data = news.text if news.text != '' else ''
publish_date = Helper.parse_date(publish_date_data)
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"url":
url,
"link":
url,
"news_url_uid":
hashlib.md5(url.encode()).hexdigest(),
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"fujielectric",
"ticker":
"fujielectric_scrapped",
"industry_name":
"fujielectric",
"news_provider":
"fujielectric"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, 'fujielectric_news')
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']) > 0:
bulk_obj.execute()
else:
print("News Not Found")
def crawler_news(self):
try:
loop = True
while loop:
response = crawler.MakeRequest(self.url,
'Post',
postData=self.body,
headers=self.headers)
soup = BeautifulSoup(response.content, 'html.parser')
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
news_data = json.loads(response.content.decode('utf-8'))
if news_data:
for news in news_data[:1]:
news_dict = Helper.get_news_dict()
title = news['Title'] if 'Title' in news else ''
# Check if already present
unqUrl = hashlib.md5(title.encode()).hexdigest()
chkIsExists = DbOperations.GetData(
self.news_collection,
{"news_title_uid": str(unqUrl)}, {}, QueryType.one)
if (chkIsExists):
print("Already saved. title - ( " + title + " )")
continue
publish_date_data = news[
'EntryDate'] if 'EntryDate' in news else ''
publish_date = Helper.parse_date(publish_date_data)
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"omron",
"ticker":
"omron_scrapped",
"industry_name":
"omron",
"news_provider":
"omron"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.
__dict__['ops']) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 0:
bulk_obj.execute()
self.body['StartRange'] += 1
else:
print("All news has been scrapped !!")
loop = False
except Exception as e:
self.logger.error(f"Error Occured : \n", exc_info=True)
def crawler_news(self):
try:
response = crawler.MakeRequest(self.url,
'Get',
postData=self.body,
headers=self.headers)
soup = BeautifulSoup(response.content, 'html.parser')
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
news_data = json.loads(response.content.decode('utf-8'))
if news_data:
for news in news_data['GetPressReleaseListResult']:
news_dict = Helper.get_news_dict()
title = news['Headline'] if 'Headline' in news else ""
url = "https://www.craneco.com" + str(
news['LinkToDetailPage']
) if 'LinkToDetailPage' in news else ''
# Check if already present
unqUrl = hashlib.md5(url.encode()).hexdigest()
chkIsExists = DbOperations.GetData(
self.news_collection, {"news_url_uid": str(unqUrl)},
{}, QueryType.one)
if (chkIsExists):
print("Already saved. url - ( " + url + " )")
continue
publish_date = Helper.parse_date(
news['PressReleaseDate']
) if 'PressReleaseDate' in news else ''
url_response = crawler.MakeRequest(url,
'Get',
postData=self.body,
headers=self.headers)
url_soup = BeautifulSoup(url_response.content,
'html.parser')
description_data = url_soup.find(
'div', {'class': "module_body clearfix"})
description = []
regex = re.compile(r'[\n\xa0]')
for desc in description_data.find_all('p'):
description.append(regex.sub("", str(desc.text)))
description = ''.join(description)
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"url":
url,
"link":
url,
"news_url_uid":
hashlib.md5(url.encode()).hexdigest(),
"description":
description,
"text":
description,
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"crane",
"ticker":
"crane_scrapped",
"industry_name":
"crane",
"news_provider":
"crane"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 0:
bulk_obj.execute()
else:
print("All news has been scrapped !!")
except Exception as e:
self.logger.error(f"Error Occured : \n", exc_info=True)
def crawler_news(self):
try:
loop = True
page = 1
while loop:
response = crawler.MakeRequest(self.url.format(page=page),
'Get',
postData=self.body,
headers=self.headers)
soup = BeautifulSoup(response.content, 'html.parser')
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
news_data = soup.find('tbody')
if news_data and news_data.tr.text.strip(
) != 'There is no data.':
for news in news_data.find_all('tr'):
news_dict = Helper.get_news_dict()
title_data = news.find('td', {'class': 'title'})
title = title_data.text if title_data else ""
# Check if already present
unqUrl = hashlib.md5(title.encode()).hexdigest()
chkIsExists = DbOperations.GetData(
self.news_collection,
{"news_title_uid": str(unqUrl)}, {}, QueryType.one)
if (chkIsExists):
print("Already saved. title - ( " + title + " )")
continue
publish_date_data = news.find_all('td')[3].text
publish_date = Helper.parse_date(
publish_date_data
) if publish_date_data and publish_date_data != '' else ''
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"hanwhacorp",
"ticker":
"hanwhacorp_scrapped",
"industry_name":
"hanwhacorp",
"news_provider":
"hanwhacorp"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.
__dict__['ops']) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 0:
bulk_obj.execute()
page += 1
else:
print("All news has been scrapped !!")
loop = False
except Exception as e:
self.logger.error(f"Error Occured : \n", exc_info=True)
def crawler_news(self):
response = crawler.MakeRequest(self.url,
'Get',
postData=self.body,
headers=self.headers)
soup = BeautifulSoup(response.content, 'html.parser')
bulk_obj = DbOperations.Get_object_for_bulkop(False, 'enersys_news')
news_data = soup.find(
'div', {'class': "content-listing__items glide__slides"})
if news_data:
for news in news_data.find_all(
'a',
{'class': 'content-listing__item glide__slide col-lg-3 '}):
news_dict = Helper.get_news_dict()
regex = re.compile(r'[\r\n\xa0]')
title_data = news.find('h3')
title = regex.sub("", str(
title_data.text.strip())) if title_data else ""
url = "https://www.enersys.com" + str(news['href'])
publish_date_data = news.find(
'p', {'class': 'content-listing__item-date'})
publish_date = Helper.parse_date(
publish_date_data.text.strip()
) if publish_date_data and publish_date_data.text != '' else ''
url_response = crawler.MakeRequest(url,
'Get',
postData=self.body,
headers=self.headers)
url_soup = BeautifulSoup(url_response.content, 'html.parser')
description_data = url_soup.find(
'div', {'class': "standard-page__body"})
description = []
for desc in description_data.find_all('p'):
description.append(regex.sub("", str(desc.text)))
description = ''.join(description)
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"url":
url,
"link":
url,
"news_url_uid":
hashlib.md5(url.encode()).hexdigest(),
"description":
description,
"text":
description,
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"enersys",
"ticker":
"enersys_scrapped",
"industry_name":
"enersys",
"news_provider":
"enersys"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, 'enersys_news')
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']) > 0:
bulk_obj.execute()
else:
print("News Not Found")
def crawler_news(self):
response = crawler.MakeRequest(self.url,
'Get',
postData=self.body,
headers=self.headers)
soup = BeautifulSoup(response.content, 'html.parser')
bulk_obj = DbOperations.Get_object_for_bulkop(False, 'olympus_news')
news_data = soup.find('ul', {'class': "list-news-01"})
if news_data:
for news in news_data.find_all('li'):
news_dict = Helper.get_news_dict()
title_data = news.find('span', {'class': 'text'})
title = title_data.text if title_data else ""
url_data = news.find('a', {'href': True})
url = "https://www.olympus-global.com" + str(
url_data['href']) if url_data else ''
publish_date_data = news.find('span', {'class': 'date'})
publish_date = Helper.parse_date(
publish_date_data.text
) if publish_date_data and publish_date_data.text != '' else ''
url_response = crawler.MakeRequest(url,
'Get',
postData=self.body,
headers=self.headers)
url_soup = BeautifulSoup(url_response.content, 'html.parser')
description_data = url_soup.find('div',
{'class': "area-content"})
description = []
regex = re.compile(r'[\n\xa0]')
for desc in description_data.find_all('b'):
description.append(regex.sub("", str(desc.text.strip())))
description = ''.join(description)
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"url":
url,
"link":
url,
"news_url_uid":
hashlib.md5(url.encode()).hexdigest(),
"description":
description,
"text":
description,
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"olympus",
"ticker":
"olympus_scrapped",
"industry_name":
"olympus",
"news_provider":
"olympus"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, 'olympus_news')
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']) > 0:
bulk_obj.execute()
else:
print("News Not Found")
def crawler_news(self):
try:
response = crawler.MakeRequest(self.url,
'Get',
postData=self.body,
headers=self.headers)
soup = BeautifulSoup(response.content, 'html.parser')
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
article_data = soup.find_all('div', {'class': 'article'})
if article_data:
for article in article_data:
news_data = article.find_all('section', {'class': ""})
for news in news_data[1::2]:
news_dict = Helper.get_news_dict()
title_data = news.find('h2')
title = title_data.text if title_data else ""
url = news.find_next_sibling(
).a['href'] if news.find_next_sibling() else ''
# Check if already present
unqUrl = hashlib.md5(url.encode()).hexdigest()
chkIsExists = DbOperations.GetData(
self.news_collection,
{"news_url_uid": str(unqUrl)}, {}, QueryType.one)
if (chkIsExists):
print("Already saved. url - ( " + url + " )")
continue
description_data = news.find('p')
description = description_data.text if description_data else ''
url_response = crawler.MakeRequest(
url,
'Get',
postData=self.body,
headers=self.headers)
url_soup = BeautifulSoup(url_response.content,
'html.parser')
publish_date_data = url_soup.find(
'p', {'class': 'meta large inline'})
publish_date = Helper.parse_date(
publish_date_data.text.replace('|', "").strip()
) if publish_date_data and publish_date_data.text != '' else ''
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"url":
url,
"link":
url,
"news_url_uid":
hashlib.md5(url.encode()).hexdigest(),
"description":
description,
"text":
description,
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"voestalpine",
"ticker":
"voestalpine_scrapped",
"industry_name":
"voestalpine",
"news_provider":
"voestalpine"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.
__dict__['ops']) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 0:
bulk_obj.execute()
except Exception as e:
self.logger.error(f"Error Occured : \n", exc_info=True)
def crawler_news(self):
try:
loop = True
page = 0
while loop:
response = crawler.MakeRequest(
self.url,
'Post',
postData=self.body.format(page=page),
headers=self.headers)
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
news_data = json.loads(response.content.decode('utf-8'))
if news_data['News']:
for news in news_data['News']:
news_dict = Helper.get_news_dict()
title = news['Title'] if 'Title' in news else ''
url = "https://www.novozymes.com" + str(
news['Url']) if 'Url' in news else ''
# Check if already present
unqUrl = hashlib.md5(url.encode()).hexdigest()
chkIsExists = DbOperations.GetData(
self.news_collection,
{"news_url_uid": str(unqUrl)}, {}, QueryType.one)
if (chkIsExists):
print("Already saved. url - ( " + url + " )")
continue
publish_date_data = news[
'CreationDate'] if 'CreationDate' in news else ''
publish_date = Helper.parse_date(publish_date_data)
description = news[
'Content'] if 'Content' in news else ''
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"url":
url,
"link":
url,
"news_url_uid":
hashlib.md5(url.encode()).hexdigest(),
"description":
description,
"text":
description,
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"novozymes",
"ticker":
"novozymes_scrapped",
"industry_name":
"novozymes",
"news_provider":
"novozymes"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.
__dict__['ops']) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 0:
bulk_obj.execute()
page += 1
else:
print("All news has been scrapped !!")
loop = False
except Exception as e:
self.logger.error(f"Error Occured : \n", exc_info=True)
def crawler_news(self):
try:
loop = True
page = 1
while loop:
response = crawler.MakeRequest(self.url.format(page=page),
'Get',
postData=self.body)
soup = BeautifulSoup(response.content, 'html.parser')
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
news_data = soup.find_all('div',
{'class': "contentCollection--item"})
if news_data:
for news in news_data:
news_dict = Helper.get_news_dict()
title_data = news.find('a')
title = title_data.text if title_data else ""
url_data = news.find('a', {'href': True})
url = "https://corporate.exxonmobil.com" + str(
url_data['href']) if url_data else ''
# Check if already present
unqUrl = hashlib.md5(url.encode()).hexdigest()
chkIsExists = DbOperations.GetData(
self.news_collection,
{"news_url_uid": str(unqUrl)}, {}, QueryType.one)
if (chkIsExists):
print("Already saved. url - ( " + url + " )")
continue
description_data = news.find(
'span',
{'class': 'contentCollection--description p'})
description = description_data.text if description_data else ''
publish_date_data = news.find('span',
{'class': 'date'})
publish_date = Helper.parse_date(
publish_date_data.text
) if publish_date_data and publish_date_data.text != '' else ''
news_dict.update({
"title":
title,
"url":
url,
"formatted_sub_header":
title,
"description":
description,
"link":
url,
"publishedAt":
publish_date,
'date':
publish_date,
"news_provider":
"exxonmobil_corporation",
"company_id":
"exxonmobil_corporation",
"ticker":
"exxonmobil_corporation_scrapped",
"industry_name":
"exxonmobil_corporation"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.
__dict__['ops']) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 0:
bulk_obj.execute()
page += 1
else:
print("All news has been scrapped !!")
loop = False
except Exception as e:
self.logger.error(f"Error Occured : \n", exc_info=True)
def crawler_news(self):
try:
response = crawler.MakeRequest(self.url,
'Get',
postData=self.body,
headers=self.headers)
soup = BeautifulSoup(response.content, 'html.parser')
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
news_data = soup.find('ul', {'class': "newsPressList tabContent"})
if news_data:
for news in news_data.find_all('li'):
news_dict = Helper.get_news_dict()
title_data = news.find('h3')
title = title_data.text if title_data else ""
url_data = news.find('a', {'href': True})
url = url_data['href'] if url_data else ''
# Check if already present
unqUrl = hashlib.md5(url.encode()).hexdigest()
chkIsExists = DbOperations.GetData(
self.news_collection, {"news_url_uid": str(unqUrl)},
{}, QueryType.one)
if (chkIsExists):
print("Already saved. url - ( " + url + " )")
continue
publish_date_data = news.find('span', {'class': 'date'})
publish_date = Helper.parse_date(
publish_date_data.text
) if publish_date_data and publish_date_data.text != '' else ''
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"url":
url,
"link":
url,
"news_url_uid":
hashlib.md5(url.encode()).hexdigest(),
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"LnT",
"ticker":
"LnT_scrapped",
"industry_name":
"LnT",
"news_provider":
"LnT"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
if len(bulk_obj._BulkOperationBuilder__bulk.__dict__['ops']
) > 0:
bulk_obj.execute()
except Exception as e:
self.logger.error(f"Error Occured : \n", exc_info=True)
def crawler_news(self):
try:
loop = True
page = 1
while loop:
try:
response = crawler.MakeRequest(self.url.format(page=page),
'Get',
postData=self.body,
headers=self.headers)
soup = BeautifulSoup(response.content, 'html.parser')
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
news_data = soup.find_all('div', {'class': "media"})
if news_data:
for news in news_data:
news_dict = Helper.get_news_dict()
title_data = news.find('h4',
{'class': 'media-heading'})
title = title_data.text if title_data else ""
url_data = news.find('a', {'href': True})
url = "https://www.hbfuller.com" + str(
url_data['href']) if url_data else ''
# Check if already present
unqUrl = hashlib.md5(url.encode()).hexdigest()
chkIsExists = DbOperations.GetData(
self.news_collection,
{"news_url_uid": str(unqUrl)}, {},
QueryType.one)
if (chkIsExists):
print("Already saved. url - ( " + url + " )")
continue
publish_date_data = news.find(
'div', {'class': 'listing-date'})
publish_date = Helper.parse_date(
str(publish_date_data.text).strip()
) if publish_date_data and publish_date_data.text != '' else ''
url_response = crawler.MakeRequest(
url,
'Get',
postData=self.body,
headers=self.headers)
url_soup = BeautifulSoup(url_response.content,
'html.parser')
description_data = url_soup.find(
'div', {
'class': 'row ar-body'
}).find('div', {
'class': "col-xs-12 col-sm-8 col-md-9"
}).find('div', {
'class': 'col-sm-12'
}).find('div', {'style': ''})
description = description_data.text.strip().split(
'\n')
description = ''.join(description[1:])
news_dict.update({
"title":
title,
"news_title_uid":
hashlib.md5(title.encode()).hexdigest(),
"url":
url,
"link":
url,
"news_url_uid":
hashlib.md5(url.encode()).hexdigest(),
"description":
description,
"text":
description,
"publishedAt":
publish_date,
'date':
publish_date,
"publishedAt_scrapped":
publish_date,
"company_id":
"hbfuller",
"ticker":
"hbfuller_scrapped",
"industry_name":
"hbfuller",
"news_provider":
"hbfuller"
})
bulk_obj.insert(news_dict)
if len(bulk_obj._BulkOperationBuilder__bulk.
__dict__['ops']) > 100:
bulk_obj.execute()
bulk_obj = DbOperations.Get_object_for_bulkop(
False, self.news_collection)
if len(bulk_obj._BulkOperationBuilder__bulk.
__dict__['ops']) > 0:
bulk_obj.execute()
page += 1
else:
print("All news has been scrapped !!")
loop = False
except AttributeError as e:
print("All news has been scrapped !!")
loop = False
except Exception as e:
self.logger.error(f"Error Occured : \n", exc_info=True)
