def recreate_db():
try:
db.reflect()
db.drop_all()
except SQLAlchemyError as e:
raise ValueError(e)
db.create_all()
db.session.commit()
def parse_main_pages():
try:
last_article = db.session.query(Article).order_by(
Article.id.desc()).first()
max_id_pos_start = str(last_article).find("id=")
max_id_pos_end = str(last_article).find("title=")
max_id = str(last_article)[max_id_pos_start + 3:max_id_pos_end - 2]
max_id = int(max_id) + 1
except ValueError:
max_id = 1
print("max_id", max_id)
flag_old_news = 0
n_page = 0
while flag_old_news != 1:
n_page = n_page + 1
article_date = ""
print("n_page", n_page)
if n_page == 1:
url = MAIN_URL
else:
url = MAIN_URL_PAGE_FROM2 + str(n_page) + '.html'
html_page = requests.get(
url,
headers={
"user-agent":
"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:54.0)"
"Gecko/20100101 Firefox/74.0"
}).text
soup = BeautifulSoup(html_page, 'html.parser')
soup = soup.find_all("div", {"class": "st__news-list"})
all_articles = soup[0].find_all("li", {"class": ""})
all_articles2 = soup[0].find_all(
"li", {"class": "st__news st__hot-news_with-photo"})
all_articles3 = soup[0].find_all(
"li", {"class": "st__news st__news_with-photo"})
for li_link_article in all_articles2:
all_articles.append(li_link_article)
for li_link_article2 in all_articles3:
all_articles.append(li_link_article2)
print("all_articles", all_articles)
for article in all_articles:
print()
all_url_tag = article.find_all("a")
# if all_url_tag is None or all_url_tag == "":
print("all_url_tag", all_url_tag)
try:
url_article = all_url_tag[0].get("href")
url_article = BASE_URL + str(url_article)
print("url_article", url_article)
except:
print("CONTINUE")
continue
article_title, article_date, article_text = parse_article_pages(
url_article)
article_text = str(article_text).strip()
print("article_title", article_title)
if article_title == "":
continue
try:
db.session.rollback()
if db.session.query(Article.id).filter_by(
title=article_title).scalar() is not None:
print("Found in db")
continue
except sqlite3.IntegrityError:
continue
except sqlalchemy.exc.IntegrityError:
continue
resource = "https://euvsdisinfo.eu/"
print("article_text", article_text)
print("article_date", article_date)
translator = Translator()
try:
src_lang = translator.translate(article_title).src
except json.decoder.JSONDecodeError:
time.sleep(3)
translator = Translator()
src_lang = translator.translate(article_title).src
# REINITIALIZE THE API
translator = Translator()
try:
translated = translator.translate(article_title,
src=src_lang,
dest="en")
article_title_en = translated.text
except Exception as e:
print(str(e))
article_title_en = ""
print("article_title_en", article_title_en)
article_text = str(article_text).strip()
article_date = str(article_date).strip()
new_article = Article(id=max_id,
title=article_title,
title_en=article_title_en,
text=article_text,
date=article_date,
resource=resource,
url=url_article)
max_id += 1
try:
db.session.add(new_article)
db.session.commit()
db.session.flush()
db.create_all()
except sqlalchemy.exc.IntegrityError:
continue
except sqlalchemy.exc.DataError:
continue
if n_page >= 700:
flag_old_news = 1
def parse_main_pages():
"""parse main pages to get main url and titles"""
urls_article = []
n_article = -1
try:
last_article = db.session.query(ArticleFakeChecker2).order_by(ArticleFakeChecker2.id.desc()).first()
max_id_pos_start = str(last_article).find("id=")
max_id_pos_end = str(last_article).find("title=")
max_id = str(last_article)[max_id_pos_start + 3: max_id_pos_end - 2]
max_id = int(max_id) + 1
except ValueError:
max_id = 1
print("max_id", max_id)
for n_page in range(44, NUMBER_PAGES):
print("n_page", n_page + 1)
if n_page + 1 == 1:
url = MAIN_URL
else:
url = MAIN_URL_PAGE_FROM2 + str(n_page + 1) + '/'
html_page = requests.get(url,
headers={
"user-agent": "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:54.0)"
"Gecko/20100101 Firefox/74.0"}, verify=False).text
soup = BeautifulSoup(html_page, 'html.parser')
all_articles = soup.find_all("article")
flag_video = 0
for article in all_articles:
all_span = article.find_all("span", {"class": "post-category"})
n_article += 1
for span in all_span:
if "Відео" in str(span):
flag_video = 1
break
if flag_video == 1:
flag_video = 0
continue
all_a = article.find_all("a")
url_article = all_a[0].get("href")
urls_article.append(url_article)
print()
article_title, article_date, article_text = parse_article_pages(url_article)
article_text = str(article_text).strip()
print("article_title", article_title)
try:
db.session.rollback()
if db.session.query(ArticleFakeChecker2.id).filter_by(title=article_title).scalar() is not None:
print("Found in db")
continue
except sqlite3.IntegrityError:
continue
except sqlalchemy.exc.IntegrityError:
continue
translator = Translator()
try:
src_lang = translator.translate(article_title).src
except json.decoder.JSONDecodeError:
time.sleep(3)
translator = Translator()
src_lang = translator.translate(article_title).src
# REINITIALIZE THE API
translator = Translator()
try:
translated = translator.translate(article_title, src=src_lang, dest="en")
article_title_en = translated.text
except Exception as e:
print(str(e))
article_title_en = ""
resource_end_pos = url_article.find("/uk")
resource = url_article[:resource_end_pos + 3]
print("article_text", article_text)
new_article = ArticleFakeChecker2(id=max_id,
title=article_title,
title_en=article_title_en,
text=article_text,
date=article_date,
resource=resource,
url=url_article)
max_id += 1
try:
db.session.add(new_article)
db.session.commit()
db.session.flush()
db.create_all()
except sqlalchemy.exc.IntegrityError:
continue
except sqlalchemy.exc.DataError:
continue
try:
db.session.rollback()
db.session.commit()
db.create_all()
except sqlalchemy.exc.IntegrityError:
continue
def parse_all_pages(filename):
"""parse main pages to get all data"""
with open(filename, "r", encoding="utf-8") as file:
urls_article = json.load(file)
try:
last_article = db.session.query(Article).order_by(
Article.id.desc()).first()
max_id_pos_start = str(last_article).find("id=")
max_id_pos_end = str(last_article).find("title=")
max_id = str(last_article)[max_id_pos_start + 3:max_id_pos_end - 2]
max_id = int(max_id) + 1
except ValueError:
max_id = 1
print("max_id", max_id)
for url in urls_article["urls_explorer"]:
html_page = requests.get(
url,
headers={
"user-agent":
"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:54.0)"
"Gecko/20100101 Firefox/74.0"
},
verify=False).text
soup = BeautifulSoup(html_page, 'html.parser')
try:
all_h = soup.find_all("h1", {"class": "news-full__title"})
article_title = all_h[0].string
article_title = str(article_title).strip()
except Exception as e:
print(str(e))
continue
print()
print("article_title", article_title)
try:
db.session.rollback()
if db.session.query(Article.id).filter_by(
title=article_title).scalar() is not None:
print("Found in db")
continue
except sqlite3.IntegrityError:
continue
except sqlalchemy.exc.IntegrityError:
continue
try:
all_div = soup.find_all(
"div", {"class": "news-full__text io-article-body"})
article_text = all_div[0]
article_text = BeautifulSoup(str(article_text).strip(),
"lxml").text
article_text = str(article_text).strip()
except Exception as e:
print(str(e))
article_text = ""
print("article_text", article_text)
try:
article_date = soup.find_all(
"time", {"class": "news-full__date--create"})[0].string
article_date = str(article_date).strip()
except Exception as e:
print(str(e))
article_date = ""
print("article_date", article_date)
resource = "https://www.obozrevatel.com/"
if article_title != "":
article_title_en = translate_title(article_title)
else:
article_title_en = ""
new_article = Article(id=max_id,
title=article_title,
title_en=article_title_en,
text=article_text,
date=article_date,
resource=resource,
url=url)
max_id += 1
print("article_title_en", article_title_en)
try:
db.session.rollback()
db.session.add(new_article)
db.session.commit()
db.session.flush()
db.create_all()
except sqlalchemy.exc.IntegrityError:
continue
except sqlalchemy.exc.DataError:
continue
def init_request():
db.create_all()
def parse_main_pages(site_name, url_main, url_page2, class_articles,
class_title, class_date, class_text):
"""parse pages to get main information"""
try:
last_article = db.session.query(ArticleFakeChecker2).order_by(
ArticleFakeChecker2.id.desc()).first()
max_id_pos_start = str(last_article).find("id=")
max_id_pos_end = str(last_article).find("title=")
max_id = str(last_article)[max_id_pos_start + 3:max_id_pos_end - 2]
max_id = int(max_id) + 1
except ValueError:
max_id = 1
print("max_id", max_id)
flag_old_news = 0
n_page = 0
while flag_old_news != 1:
n_page = n_page + 1
article_date = ""
print("n_page", n_page)
if n_page == 1:
url = url_main
else:
if site_name == "obozrevatel":
url = url_page2 + str(n_page + 1) + '/'
else:
url = url_page2 + str(n_page + 1) + '/'
html_page = requests.get(
url,
headers={
"user-agent":
"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:54.0)"
"Gecko/20100101 Firefox/74.0"
},
verify=False).text
soup = BeautifulSoup(html_page, 'html.parser')
all_articles = soup.find_all("a", {"class": "b-post__link"})
for article in all_articles:
print()
url_article = article.get("href")
article_title, article_date, article_text = parse_article_pages(
url_article, class_title, class_date, class_text)
article_text = str(article_text).strip()
print("article_title", article_title)
try:
db.session.rollback()
if db.session.query(ArticleFakeChecker2.id).filter_by(
title=article_title).scalar() is not None:
print("Found in db")
continue
except sqlite3.IntegrityError:
continue
except sqlalchemy.exc.IntegrityError:
continue
if site_name == "euvsdisinfo":
resource = "https://euvsdisinfo.eu/"
new_article = ArticleFakeChecker2(id=max_id,
title=article_title,
title_en=article_title,
text=article_text,
date=article_date,
resource=resource,
url=url_article)
elif site_name == "obozrevatel":
resource = "https://www.obozrevatel.com/"
if article_title != "":
article_title_en = translate_title(article_title)
else:
article_title_en = ""
new_article = Article(id=max_id,
title=article_title,
title_en=article_title_en,
text=article_text,
date=article_date,
resource=resource,
url=url)
print("article_text", article_text)
print("article_date", article_date)
max_id += 1
try:
db.session.add(new_article)
db.session.commit()
db.session.flush()
db.create_all()
except sqlalchemy.exc.IntegrityError:
continue
except sqlalchemy.exc.DataError:
continue
if str(article_date).split(
", ")[-1].strip() == "2018" or n_page >= 700:
flag_old_news = 1
try:
db.session.rollback()
db.session.commit()
db.create_all()
except sqlalchemy.exc.IntegrityError:
continue
from flask_app.app import db db.create_all()
def parse_main_pages():
"""parse main pages to get all data"""
try:
last_article = db.session.query(Article).order_by(
Article.id.desc()).first()
max_id_pos_start = str(last_article).find("id=")
max_id_pos_end = str(last_article).find("title=")
max_id = str(last_article)[max_id_pos_start + 3:max_id_pos_end - 2]
max_id = int(max_id) + 1
except ValueError:
max_id = 1
n_article = -1
print("max_id", max_id)
for n_page in range(500, NUMBER_PAGES):
print("n_page", n_page + 1)
if n_page + 1 == 1:
url = MAIN_URL
else:
url = MAIN_URL_PAGE_FROM2 + str(n_page + 1) + '/'
stop_requests = 0
flag_bad_request_for_page = 0
session = requests.Session()
session.max_redirects = 60
while str(
session.get(url,
headers={
"user-agent":
"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:54.0)"
"Gecko/20100101 Firefox/74.0"
})).strip() != "<Response [200]>":
time.sleep(3)
stop_requests += 1
if stop_requests == 10:
print()
print("error!!!!!!!!!!!!!!!", session.get(url))
flag_bad_request_for_page = 1
break
if flag_bad_request_for_page == 1:
continue
html_page = session.get(
url,
headers={
"user-agent":
"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:54.0)"
"Gecko/20100101 Firefox/74.0"
}).text
soup = BeautifulSoup(html_page, 'html.parser')
all_span = soup.find_all("a", {"class": "lbn_link"})
n_article += 1
for span in all_span:
if "Відео" in str(span):
continue
url_article = span.get("href")
print()
article_title, article_date, article_text = parse_article_pages(
url_article)
if article_title is None:
continue
article_text = str(article_text).strip()
print("article_title", article_title)
try:
db.session.rollback()
if db.session.query(Article.id).filter_by(
title=article_title).scalar() is not None:
print("Found in db")
continue
except sqlite3.IntegrityError:
continue
except sqlalchemy.exc.IntegrityError:
continue
translator = Translator()
try:
src_lang = translator.translate(article_title).src
except json.decoder.JSONDecodeError:
time.sleep(3)
translator = Translator()
src_lang = translator.translate(article_title).src
# REINITIALIZE THE API
translator = Translator()
try:
translated = translator.translate(article_title,
src=src_lang,
dest="en")
article_title_en = translated.text
except Exception as e:
print(str(e))
article_title_en = ""
resource_end_pos = url_article.find("/ua")
resource = url_article[:resource_end_pos + 3]
print("article_text", article_text)
new_article = Article(id=max_id,
title=article_title,
title_en=article_title_en,
text=article_text,
date=article_date,
resource=resource,
url=url_article)
max_id += 1
try:
db.session.add(new_article)
db.session.commit()
db.session.flush()
db.create_all()
except sqlalchemy.exc.IntegrityError:
continue
try:
db.session.rollback()
db.session.commit()
db.create_all()
except sqlalchemy.exc.IntegrityError:
continue
