Spaces:
Running
Running
:gem: [Feature] New HTMLFetcher: download url to local html file
Browse files- networks/filepath_converter.py +7 -7
- networks/html_fetcher.py +44 -0
networks/filepath_converter.py
CHANGED
@@ -71,7 +71,7 @@ class FilepathConverter:
|
|
71 |
self.filename = filename
|
72 |
self.filepath = filepath
|
73 |
|
74 |
-
return
|
75 |
|
76 |
|
77 |
class UrlToFilepathConverter(FilepathConverter):
|
@@ -93,12 +93,12 @@ class QueryToFilepathConverter(FilepathConverter):
|
|
93 |
if __name__ == "__main__":
|
94 |
query = "python ζη¨"
|
95 |
query_converter = QueryToFilepathConverter()
|
96 |
-
print(query_converter.convert(query)
|
97 |
|
98 |
# url = "https://trafilatura.readthedocs.io/en/latest/quickstart.html"
|
99 |
-
url =
|
100 |
-
|
101 |
-
|
102 |
-
|
103 |
url_converter = UrlToFilepathConverter()
|
104 |
-
print(url_converter.convert(url, parent=query)
|
|
|
71 |
self.filename = filename
|
72 |
self.filepath = filepath
|
73 |
|
74 |
+
return self.filepath
|
75 |
|
76 |
|
77 |
class UrlToFilepathConverter(FilepathConverter):
|
|
|
93 |
if __name__ == "__main__":
|
94 |
query = "python ζη¨"
|
95 |
query_converter = QueryToFilepathConverter()
|
96 |
+
print(query_converter.convert(query))
|
97 |
|
98 |
# url = "https://trafilatura.readthedocs.io/en/latest/quickstart.html"
|
99 |
+
url = (
|
100 |
+
"https://stackoverflow.com/questions/295135/turn-a-string-into-a-valid-filename"
|
101 |
+
)
|
102 |
+
|
103 |
url_converter = UrlToFilepathConverter()
|
104 |
+
print(url_converter.convert(url, parent=query))
|
networks/html_fetcher.py
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import requests
|
2 |
+
from pathlib import Path
|
3 |
+
from utils.enver import enver
|
4 |
+
from utils.logger import logger
|
5 |
+
from networks.filepath_converter import UrlToFilepathConverter
|
6 |
+
|
7 |
+
|
8 |
+
class HTMLFetcher:
|
9 |
+
def __init__(self):
|
10 |
+
self.enver = enver
|
11 |
+
self.enver.set_envs(proxies=True)
|
12 |
+
|
13 |
+
def send_request(self):
|
14 |
+
logger.note(f"Fetching: [{self.url}]")
|
15 |
+
self.request_response = requests.get(
|
16 |
+
url=self.url,
|
17 |
+
headers={
|
18 |
+
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36 Edg/111.0.1661.62",
|
19 |
+
},
|
20 |
+
proxies=self.enver.requests_proxies,
|
21 |
+
)
|
22 |
+
|
23 |
+
def save_response(self):
|
24 |
+
self.save_path = UrlToFilepathConverter().convert(self.url)
|
25 |
+
if not self.save_path.exists():
|
26 |
+
self.save_path.parent.mkdir(parents=True, exist_ok=True)
|
27 |
+
|
28 |
+
logger.success(f"Saving to: [{self.save_path}]")
|
29 |
+
|
30 |
+
with open(self.save_path, "wb") as wf:
|
31 |
+
wf.write(self.request_response.content)
|
32 |
+
|
33 |
+
def fetch(self, url):
|
34 |
+
self.url = url
|
35 |
+
self.send_request()
|
36 |
+
self.save_response()
|
37 |
+
|
38 |
+
|
39 |
+
if __name__ == "__main__":
|
40 |
+
url = (
|
41 |
+
"https://stackoverflow.com/questions/295135/turn-a-string-into-a-valid-filename"
|
42 |
+
)
|
43 |
+
fetcher = HTMLFetcher()
|
44 |
+
fetcher.fetch(url)
|