1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
|
from bs4 import BeautifulSoup
from markdownify import markdownify
from requests.exceptions import HTTPError
import requests
class WikiError(Exception):
pass
def fix_link(config, node, field):
node[field] = node[field].replace("/wiki", config["site"] + "/wiki")
def get_search_response(config, query):
try:
response = requests.get(config['site'] + '/mediawiki/api.php?action=opensearch&format=json&formatversion=2&search=' + query + '&namespace=0&limit=6&suggest=true', timeout=7)
except requests.exceptions.Timeout:
raise WikiError("Request timed out.")
except requests.exceptions.RequestException as e:
print(f"Failed to complete request: {e}")
raise WikiError("Error with wiki request.")
try:
response.raise_for_status()
except HTTPError as e:
print(f"HTTP error occured: {e}")
raise WikiError("Bad HTTP response.")
data = response.json()
if not data[3]:
raise WikiError("No such wiki entry found.")
return data[3]
def get_page_content(config, page_name):
try:
response = requests.get(page_name, timeout=7)
except requests.exceptions.Timeout:
raise WikiError("Request timed out.")
except requests.exceptions.RequestException as e:
print(f"Failed to complete request: {e}")
raise WikiError("Error with wiki request.")
try:
response.raise_for_status()
except HTTPError as e:
print(f"HTTP error occured: {e}")
raise WikiError("Bad HTTP response.")
soup = BeautifulSoup(response.content, "html.parser")
parser_output = soup.find(id="mw-content-text").contents[0]
content = parser_output.find("p")
for a in content.findAll("a"):
fix_link(config, a, "href")
image = parser_output.find("a", {"class": "image"})
image_link = None
if image:
if image.contents[0]:
fix_link(config, image.contents[0], "src")
image_link = image.contents[0]["src"]
header_md = markdownify(str(soup.find(id="firstHeading").contents[0]))
content_md = markdownify(str(content))
return header_md, content_md, image_link
|
