def recuperation_info_lmde(
file_target="data/clean/robot/" + str(date.datetime.now().date()) + "/"):
source = "lemonde/"
url_rss_lib = "http://www.lemonde.fr/rss/"
abbreviation = "lmde"
url = "http://www.lemonde.fr"
list_articles = []
i = 0
listRSS = linkRSS(url_rss_lib)
for article_link in listRSS:
if "/article/" in article_link:
i += 1
list_articles.append(info_articles(article_link))
if i == 20:
utilsg4.create_json(
file_target, list_articles, source, abbreviation)
i = 0
list_articles = []
# links = recent(url)
# list_articles.extend(articlesList(links))
utilsg4.create_json(file_target, list_articles, source, abbreviation)
def recovery_new_articles_fusc(file_target = '/var/www/html/projet2018/data/clean/robot/'):
"""
it create a json for each new article
"""
links = recovery_link_new_articles('https://www.futura-sciences.com/' +
'flux-rss/')
list_articles = []
for article in links:
new_article = recovery_information_fusc(article)
if not utils.is_empty(new_article):
list_articles.append(new_article)
utils.create_json(file_target, list_articles, 'FuturaSciences', 'fusc')
def recovery_new_article_lg(file_target = "/var/www/html/projet2018/data/clean/robot/"):
"""
Retrieving new articles thanks to the rss feed
and create for each article a json
"""
url_rss = "http://www.legorafi.fr/feed/"
links_article = recovery_link_new_articles_lg(url_rss)
list_article = []
for link_article in links_article:
new_article = recovery_information_lg(link_article)
if new_article["theme"] != "Magazine":
list_article.append(new_article)
utils.create_json(file_target, list_article, "LeGorafi", "lg")
def recovery_new_articles_hum(file_target="data/clean/robot/" +
str(date.datetime.now().date()) + "/"):
"""
Returns:
- creation of a json for each new article
"""
file_json = []
# Each url is analized one by one
article_humanite = recovery_link_new_articles_hum("https://www.humanite" +
".fr/rss/actu.rss")
for article in article_humanite:
file_json.append(recovery_information_hum(article))
utils.create_json(file_target, file_json, "Humanite/",
"hum")
def add_articles(file_target="data/clean/robot/" +
str(date.datetime.now().date()) + "/"):
"""
it create a json for each new article
"""
soup = utils.recovery_flux_url_rss(
"http://www.20minutes.fr/feeds/rss-actu-france.xml")
items = soup.find_all("item")
articles = []
for item in items:
# Récuperer le lien des articles
url = re.search(r"<link/>(.*)<pubdate>", str(item)).group(1)
if is_article(url):
articles.append(get_article(url))
utils.create_json(file_target, articles, "Minutes/", "min")
def recovery_new_articles_ld(file_target="data/clean/robot/" +
str(date.datetime.now().date()) + "/"):
links = recovery_link_new_articles_ld(
"https://www.ladepeche.fr/services/flux-rss/")
list_articles = []
i = 0
for article in links:
new_article = recovery_information_ld(article)
list_articles.append(new_article)
i += 1
if i == 50:
utilsg4.create_json(file_target, list_articles, "ladepeche/", "LD")
i = 0
list_articles = []
utilsg4.create_json(file_target, list_articles, "ladepeche/", "LD")
def add_articles(
file_target="/home/etudiant/Documents/ProjetSID/Groupe4_Robot/Telerama/Art/" +
str(
date.datetime.now().date()) +
"/"):
"""
it create a json for each new article
"""
categories = {
"cinema": 40,
"scenes": 30,
"enfants": 3,
"idees": 30,
}
articles = []
for category, nbre in categories.items():
for i in range(0, nbre):
url = "http://www.telerama.fr/" + \
category + "/articles?page=" + str(i)
articles.extend(get_article_of_category(url))
utils.create_json(file_target, articles, "Telerama/", "tera")
def recovery_old_articles_sv(
file_target="C:/Users/Laetitia/Desktop/Groupe4_Robot" + str(
date.datetime.now().date()) + "/"):
"""
Returns:
- creation of a json for each new article
"""
list_category = [
"corps-et-sante",
"nature-et-enviro",
"ciel-et-espace",
"technos-et-futur",
"cerveau-et-intelligence",
"science-et-culture"]
file_json = []
for cat in list_category:
# We retrieve the URL feeds for each page of article
# Each HTML-coded article is analyzed with beautiful soup
url_rss_sv = url_rss = "https://www.science-et-vie.com/" + cat
soup_url = utils.recovery_flux_url_rss(url_rss_sv)
article_sv = []
# We retrieve all the articles for a given page
for div in soup_url.find_all("div"):
if div.get("class") == ["title"]:
for item in div.find_all("a"):
links = "https://www.science-et-vie.com/" + \
str(item.get("href"))
article_sv.append(links)
# Each article is analized one by one
for article in article_sv:
file_json.append(recovery_information_sv(article))
utils.create_json(file_target, file_json, "Scienceetvie_crawler/",
"sv")
def recovery_new_articles_fem(file_target="data/clean/robot/" +
str(date.datetime.now().date()) + "/"):
"""
Returns:
- creation of a json for each new article
"""
file_json = []
i = 0
article_fem = recovery_link_new_articles_fem()
for article in article_fem:
new_article = recovery_information_fem(article)
if utils.is_empty(new_article) is False:
file_json.append(new_article)
i += 1
if i == 20:
utils.create_json(file_target, file_json, "Femina_crawler/",
"fem")
i = 0
file_json = []
utils.create_json(file_target, file_json, "Femina_crawler/",
"fem")
def recovery_new_articles_noob_rss(file_target="data/clean/robot/" +
str(date.datetime.now().date()) + "/"):
"""
Returns:
- creation of a json for each new article
"""
file_json = []
i = 0
# Each url is analized one by one
list_url = recovery_link_new_articles_noob_rss("http://www.nouvelobs." +
"com/rss/")
for url in list_url:
soup_url = utils.recovery_flux_url_rss(url)
items = soup_url.find_all("item")
article_noob = []
# We're picking up every new article in a list
for item in items:
link_article = re.search(r"<link/>(.*)", str(item))[1]
link_article = link_article.split("<description>")
link_article = link_article[0]
article_noob.append(link_article)
if re.search("\/galeries\-photos\/", link_article):
article_noob.remove(link_article)
# Each article is analized one by one
for article in article_noob:
new_article = recovery_information_noob(article)
if utils.is_empty(new_article) is False:
file_json.append(new_article)
i += 1
if i == 20:
utils.create_json(file_target, file_json, "NouvelObs_rss/", "noob")
i = 0
file_json = []
utils.create_json(file_target, file_json, "NouvelObs/", "noob")
