def search_google_(target): engine = Google() results = engine.search("'" + target + "'") for r in results: print("|") print("|----[INFO][GOOGLE][RESULTS][>] " + r["title"]) print("|----[INFO][GOOGLE][RESULTS][DESCRIPTION][>] " + r["text"]) print("|----[INFO][GOOGLE][RESULTS][LINK][>] " + r["link"]) try: tsd, td, tsu = extract(r["link"]) domain = td + '.' + tsu spain_newspaper = open("data/newspaper/spain-newspaper.txt", "r") for news in spain_newspaper: if domain == news.strip(): newspaper.news_parser(r["link"], target) else: if not domain in config.BL_parserPhone: web = requests.get(r["link"], timeout=3) if web.status_code >= 200 or web.status_code < 300: TEXT = er.remove_tags(str(web.text)) parser.parserMAIN(TEXT) print("|") except Exception as e: print("|----[ERROR][HTTP CONNECTION][>] " + str(e))
def search_google_(target): global rep engine = Google() results = engine.search("'" + target + "'") RRSS = list() news_ = list() OTROS_ = list() for r in results: title = r["title"] link = r["link"] text = r["text"] print("|") print(f"|----[INFO][GOOGLE][RESULTS][>] {title}") print(f"|----[INFO][GOOGLE][RESULTS][DESCRIPTION][>] {text}") print(f"|----[INFO][GOOGLE][RESULTS][LINK][>] {link}") try: tsd, td, tsu = extract(link) domain = td + '.' + tsu spain_newspaper = open("data/newspaper/spain-newspaper.txt", "r") for news in spain_newspaper: if domain == news.strip(): newspaper.news_parser(link, target) news_.append(str(link)) if domain in config.BL_parserPhone: RRSS.append(str(link)) else: OTROS_.append(str(link)) print("|") except Exception as e: print("|----[ERROR][HTTP CONNECTION][>] " + str(e)) rep.add_markdown("[PRENSA]") for new in news_: rep.add_markdown(f"- Enlace: {new}") rep.add_markdown("[REDES SOCIALES]") for rrss in RRSS: rep.add_markdown(f"- Enlace: {rrss}") rep.add_markdown("[OTROS]") for otros in OTROS_: rep.add_markdown(f"- Enlace: {otros}")
def search_google_(target): global rep engine = Google() results = engine.search("'" + target + "'") RRSS = list() news_ = list() OTROS_ = list() for r in results: title = r["title"] link = r["link"] text = r["text"] try: tsd, td, tsu = extract(link) domain = td + '.' + tsu spain_newspaper = open("data/newspaper/spain-newspaper.txt", "r") for news in spain_newspaper: if domain == news.strip(): newspaper.news_parser(link, target) news_.append(str(link)) if domain in config.BL_parserPhone: RRSS.append(str(link)) else: OTROS_.append(str(link)) print("|") except Exception as e: print("|----[ERROR][HTTP CONNECTION][>] " + str(e)) print("|----[NEWSPAPERS][>] ") for new in news_: print(f"|---- ----> {new}") print("|----[SOCIAL NETWORKS][>] ") for rrss in RRSS: print(f"|---- ----> {rrss}") print("|----[OTHERS][>] ") for otros in OTROS_: print(f"|---- ----> {otros}")