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
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
|
import re
from django.apps import apps
from django.template.loader import render_to_string
from django.conf import settings
from bs4 import BeautifulSoup
import markdown
def markdown_to_html(txt):
md = markdown.Markdown(
extensions=[
'markdown.extensions.fenced_code',
'markdown.extensions.codehilite',
'markdown.extensions.attr_list',
'footnotes',
'extra'
],
extension_configs = {
'markdown.extensions.codehilite': {
'css_class': 'highlight',
'linenums': False
},
},
output_format='html5',
safe_mode=False
)
return md.convert(txt)
def extract_main_image(markdown):
soup = BeautifulSoup(markdown, 'html.parser')
try:
image = soup.find_all('img')[0]['id']
img_pk = image.split('image-')[1]
return apps.get_model('photos', 'LuxImage').objects.get(pk=img_pk)
except IndexError:
return None
def parse_image(s):
soup = BeautifulSoup(s.group(), "lxml")
for img in soup.find_all('img'):
try:
cl = img['class']
if cl[0] == 'postpic' or cl[0] == 'postpicright':
s = str(img).replace('[[base_url]]', settings.IMAGES_URL)
return s
else:
try:
image_id = img['id'].split("image-")[1]
i = apps.get_model('photos', 'LuxImage').objects.get(pk=image_id)
caption = False
exif = False
cluster_class = None
is_cluster = False
extra = None
if cl[0] == 'cluster':
css_class = cl[0]
is_cluster = True
cluster_class = cl[1]
try:
if cl[2] == 'caption':
caption = True
elif cl[2] == 'exif':
exif = True
else:
extra = cl[2]
if len(cl) > 3:
if cl[3] == 'exif':
exif = True
except:
pass
elif cl[0] != 'cluster' and len(cl) > 1:
css_class = cl[0]
if cl[1] == 'caption':
caption = True
if cl[1] == 'exif':
exif = True
elif cl[0] != 'cluster' and len(cl) > 2:
css_class = cl[0]
if cl[1] == 'caption':
caption = True
if cl[2] == 'exif':
exif = True
print('caption'+str(caption))
else:
css_class = cl[0]
return render_to_string("lib/img_%s.html" % css_class, {'image': i, 'caption': caption, 'exif': exif, 'is_cluster': is_cluster, 'cluster_class': cluster_class, 'extra': extra})
except KeyError:
''' regular inline image, not a luximage '''
return str(img)
except KeyError:
''' regular inline image, not a luximage '''
return str(img)
def render_images(s):
s = re.sub('<img(.*)/>', parse_image, s)
return s
def parse_video(s):
soup = BeautifulSoup(s, "lxml")
if soup.find('video'):
return True
return False
def parse_reg_bio_page():
content = requests.get("https://www.theregister.co.uk/Author/Scott-Gilbertson/")
soup = BeautifulSoup(content, 'html.parser')
try:
image = soup.find_all('img')[0]['id']
img_pk = image.split('image-')[1]
return apps.get_model('photos', 'LuxImage').objects.get(pk=img_pk)
except IndexError:
return None
|
