def get_article(url):
# get/parse page contents
r = requests.get(url)
r_text = r.text
soup = BeautifulSoup(r_text, "html.parser")
# get articles
page_articles = soup.find_all("div", class_="article-text category-slog")
# search articles for excerpt
for a in page_articles:
# get article content
ps_and_as = a.find_all(["p", "a"])
question = []
response = []
article_part = 1 # 1: question; 2: response
for pa in ps_and_as:
if pa.has_attr("name") and pa["name"] == "more":
article_part = 2
else:
if pa.name == "p":
if article_part == 1:
question.append(pa.get_text())
elif article_part == 2:
response.append(pa.get_text())
# if a complete article is identified, create article opject and insert it
if article_part == 2:
art = article(None, "\n".join(question), "\n".join(response))
return art
return False
def update_db(result):
for short_article in result:
a = article(canonical_name=short_article['canonical_name'], company_name=short_article['company_name'],
author=short_article.get('author',''), section=short_article
.get('section',[]), headline=short_article.get('headline',''), length=getlength(
short_article.get('length',0)), content=short_article.get('content',''),
date=getdate(short_article.get('dateline','')), location=getlocation(
short_article.get('dateline','')))
a.save()
def ajouterArticle():
if request.method == 'POST': # création article
newArticle = article(request.form["titre_article"],
request.form["Auteur_name"],
datetime.datetime.now(),
request.form["contenu_article"],
request.form["categorie_article"],
request.form["Mots_cles_article"])
if newArticle.isValid(): # vérification que l'article est valide
ajoutArticle = mongo.db.articles.insert_one(newArticle.format)
return render_template('temp_Conf_soumissionArticle.html')
else:
return render_template('template_FormArticle.html')
return render_template('template_FormArticle.html')
def valider_ajout_art():
if request.method == 'POST':
demande_art = []
demande_art.append(
mongo.db.demandes.find_one({"Mots_cles": {
'$exists': True
}}))
newArt = article(demande_art[0]["Auteur"], demande_art[0]["Titre"],
demande_art[0]["Mots_cles"],
demande_art[0]["Contenu"],
demande_art[0]["Categorie"], demande_art[0]["Date"])
ajoutArt = mongo.db.articles.insert(
newArt.format) # ajouter un utilisateur à la base de données
deleteArt = mongo.db.demandes.delete_one(
{"Mots_cles": demande_art[0]["Mots_cles"]})
line = "Félicitations! Un nouveau article est ajouté à votre base de données"
return render_template('basic.html', line=line)
return render_template("valider_ajout_article.html")
def get_article(url,txt):
txt = txt.replace('(','\(').replace(')','\)').replace('[','\[').replace(']','\]')
rX_to = re.compile('^DEAR HARRIETTE:')
rX_from = re.compile('^DEAR')
rX_excerpt = re.compile(txt)
# get/parse page contents
r = requests.get(url)
r_text = r.text
soup = BeautifulSoup(r_text, "html.parser")
# get articles
page_articles = soup.find_all("article", class_="item-section")
# search articles for excerpt
for a in page_articles:
if re.search(rX_excerpt, str(a)):
# get article content
paragraphs = a.find_all("p")
question = []
response = []
article_part = 0 # 1: question; 2: response
for p in paragraphs:
txt = p.get_text().strip()
if re.search(rX_from,txt):
if re.search(rX_to,txt):
article_part = 1
else:
article_part = 2
if article_part == 1:
question.append(txt)
elif article_part == 2:
response.append(txt)
else:
print "Error: no text matched."
# if a complete article is identified, create article opject and insert it
if article_part == 2:
art = article(None,'\n'.join(question),'\n'.join(response))
art.tags = [category.get_text().strip() for category in a.find_all("a", class_="read-more-link")]
return art
return False
