Spaces:
Paused
Paused
Update app.py
Browse files
app.py
CHANGED
|
@@ -114,7 +114,9 @@ def scrap_portal(query):
|
|
| 114 |
api_key = 'AIzaSyDJUWVZG2oHkHSsYoqdqgUZwQC2Aa2kSok'
|
| 115 |
search_engine_id = 'a0dc878459ceb4811'
|
| 116 |
num_pages = 5
|
|
|
|
| 117 |
link = []
|
|
|
|
| 118 |
|
| 119 |
for page in range(num_pages):
|
| 120 |
start_index = page * 10 + 1
|
|
@@ -218,6 +220,7 @@ def scrap_artikel(source_type,source,models,api_key,azure_api_base):
|
|
| 218 |
|
| 219 |
|
| 220 |
if source_type == "input topic":
|
|
|
|
| 221 |
link = scrap_portal(source)
|
| 222 |
for url in link:
|
| 223 |
if cek_url(url):
|
|
@@ -235,19 +238,18 @@ def scrap_artikel(source_type,source,models,api_key,azure_api_base):
|
|
| 235 |
soup_html = BeautifulSoup(raw_html, "html.parser")
|
| 236 |
containers = soup_html.findAll('p')
|
| 237 |
|
| 238 |
-
artikel =[]
|
| 239 |
for paragraph in containers:
|
| 240 |
artic=paragraph.get_text()
|
| 241 |
artikel.append(artic)
|
| 242 |
|
| 243 |
-
|
| 244 |
-
|
| 245 |
-
|
| 246 |
-
|
| 247 |
-
|
| 248 |
-
|
| 249 |
-
|
| 250 |
-
|
| 251 |
|
| 252 |
else:
|
| 253 |
wd.get(source)
|
|
@@ -703,7 +705,7 @@ with gr.Blocks(theme = "soft", title="Wordpress Article Generator") as article_g
|
|
| 703 |
with gr.Row():
|
| 704 |
with gr.Column():
|
| 705 |
source_type = gr.Radio(["input link", "input topic"], label="Source")
|
| 706 |
-
source = gr.Textbox(placeholder="Masukkan Source Link/Topik Artikel Yang Akan Digenerate", show_label=False)
|
| 707 |
backlink = gr.Textbox(placeholder="Masukkan Backlink Yang Akan Diterapkan", label="Backlink")
|
| 708 |
keyword = gr.Textbox(placeholder="Masukkan Keyword Artikel", label="Keyword")
|
| 709 |
versi = gr.Radio(["openai", "azure"], label="Request Schema", info="Pilih Skema Untuk Request ke ChatGPT ")
|
|
|
|
| 114 |
api_key = 'AIzaSyDJUWVZG2oHkHSsYoqdqgUZwQC2Aa2kSok'
|
| 115 |
search_engine_id = 'a0dc878459ceb4811'
|
| 116 |
num_pages = 5
|
| 117 |
+
type = random.choice([' articles',' news',' trends',' technologies', ' future'])
|
| 118 |
link = []
|
| 119 |
+
query = query + type
|
| 120 |
|
| 121 |
for page in range(num_pages):
|
| 122 |
start_index = page * 10 + 1
|
|
|
|
| 220 |
|
| 221 |
|
| 222 |
if source_type == "input topic":
|
| 223 |
+
artikel =[]
|
| 224 |
link = scrap_portal(source)
|
| 225 |
for url in link:
|
| 226 |
if cek_url(url):
|
|
|
|
| 238 |
soup_html = BeautifulSoup(raw_html, "html.parser")
|
| 239 |
containers = soup_html.findAll('p')
|
| 240 |
|
|
|
|
| 241 |
for paragraph in containers:
|
| 242 |
artic=paragraph.get_text()
|
| 243 |
artikel.append(artic)
|
| 244 |
|
| 245 |
+
paragraf = ' '.join(artikel)
|
| 246 |
+
if len(paragraf)>= 18000:
|
| 247 |
+
part1, part2, part3, part4 = split_article(paragraf)
|
| 248 |
+
artikels = [part1, part2, part3, part4]
|
| 249 |
+
else :
|
| 250 |
+
artikels = [paragraf]
|
| 251 |
+
title, judul, url, contents = clean_scrap(artikels,url,models,api_key,azure_api_base)
|
| 252 |
+
return title, judul, url, contents
|
| 253 |
|
| 254 |
else:
|
| 255 |
wd.get(source)
|
|
|
|
| 705 |
with gr.Row():
|
| 706 |
with gr.Column():
|
| 707 |
source_type = gr.Radio(["input link", "input topic"], label="Source")
|
| 708 |
+
source = gr.Textbox(placeholder="Masukkan Source Berupa Link/Topik Artikel Yang Akan Digenerate", show_label=False)
|
| 709 |
backlink = gr.Textbox(placeholder="Masukkan Backlink Yang Akan Diterapkan", label="Backlink")
|
| 710 |
keyword = gr.Textbox(placeholder="Masukkan Keyword Artikel", label="Keyword")
|
| 711 |
versi = gr.Radio(["openai", "azure"], label="Request Schema", info="Pilih Skema Untuk Request ke ChatGPT ")
|