uk_bin_collection 0.159.0__py3-none-any.whl → 0.159.2__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- uk_bin_collection/uk_bin_collection/councils/SouthwarkCouncil.py +62 -134
- {uk_bin_collection-0.159.0.dist-info → uk_bin_collection-0.159.2.dist-info}/METADATA +2 -2
- {uk_bin_collection-0.159.0.dist-info → uk_bin_collection-0.159.2.dist-info}/RECORD +6 -6
- {uk_bin_collection-0.159.0.dist-info → uk_bin_collection-0.159.2.dist-info}/LICENSE +0 -0
- {uk_bin_collection-0.159.0.dist-info → uk_bin_collection-0.159.2.dist-info}/WHEEL +0 -0
- {uk_bin_collection-0.159.0.dist-info → uk_bin_collection-0.159.2.dist-info}/entry_points.txt +0 -0
|
@@ -1,10 +1,40 @@
|
|
|
1
|
-
import
|
|
1
|
+
from datetime import datetime
|
|
2
|
+
|
|
2
3
|
from bs4 import BeautifulSoup
|
|
3
4
|
|
|
4
|
-
from uk_bin_collection.uk_bin_collection.common import
|
|
5
|
+
from uk_bin_collection.uk_bin_collection.common import check_uprn
|
|
5
6
|
from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataClass
|
|
6
7
|
|
|
7
8
|
|
|
9
|
+
def extract_collection_date(section, section_id):
|
|
10
|
+
"""
|
|
11
|
+
Helper function to safely extract title and collection date from a section.
|
|
12
|
+
Returns tuple (title, collection_date) or (None, None) if not found.
|
|
13
|
+
"""
|
|
14
|
+
if not section:
|
|
15
|
+
return None, None
|
|
16
|
+
|
|
17
|
+
title_element = section.find("p", {"id": section_id})
|
|
18
|
+
if not title_element:
|
|
19
|
+
return None, None
|
|
20
|
+
|
|
21
|
+
title = title_element.get_text(strip=True)
|
|
22
|
+
|
|
23
|
+
next_collection_text = section.find(
|
|
24
|
+
string=lambda t: isinstance(t, str) and "next collection" in t.lower()
|
|
25
|
+
)
|
|
26
|
+
|
|
27
|
+
if not next_collection_text:
|
|
28
|
+
return title, None
|
|
29
|
+
|
|
30
|
+
text = str(next_collection_text).strip()
|
|
31
|
+
_, sep, rhs = text.partition(":")
|
|
32
|
+
if not sep:
|
|
33
|
+
return title, None
|
|
34
|
+
collection_date = rhs.strip()
|
|
35
|
+
return title, collection_date
|
|
36
|
+
|
|
37
|
+
|
|
8
38
|
# import the wonderful Beautiful Soup and the URL grabber
|
|
9
39
|
class CouncilClass(AbstractGetBinDataClass):
|
|
10
40
|
"""
|
|
@@ -22,141 +52,39 @@ class CouncilClass(AbstractGetBinDataClass):
|
|
|
22
52
|
baseurl = "https://services.southwark.gov.uk/bins/lookup/"
|
|
23
53
|
url = baseurl + user_uprn
|
|
24
54
|
|
|
25
|
-
|
|
26
|
-
|
|
27
|
-
}
|
|
28
|
-
|
|
29
|
-
# Make the web request
|
|
30
|
-
response = requests.get(url, headers=headers).text
|
|
55
|
+
# Make the web request using the common helper (standard UA, timeout, logging)
|
|
56
|
+
response = self.get_data(url).text
|
|
31
57
|
|
|
32
58
|
soup = BeautifulSoup(response, "html.parser")
|
|
33
|
-
|
|
34
|
-
|
|
35
|
-
|
|
36
|
-
"
|
|
37
|
-
|
|
38
|
-
|
|
39
|
-
|
|
40
|
-
|
|
41
|
-
).text
|
|
42
|
-
recycling_next_collection = (
|
|
43
|
-
recycling_section.find(text=lambda text: "Next collection" in text)
|
|
44
|
-
.strip()
|
|
45
|
-
.split(": ")[1]
|
|
46
|
-
)
|
|
47
|
-
|
|
48
|
-
dict_data = {
|
|
49
|
-
"type": recycling_title,
|
|
50
|
-
"collectionDate": datetime.strptime(
|
|
51
|
-
recycling_next_collection, "%a, %d %B %Y"
|
|
52
|
-
).strftime("%d/%m/%Y"),
|
|
53
|
-
}
|
|
54
|
-
data["bins"].append(dict_data)
|
|
55
|
-
|
|
56
|
-
# Extract refuse collection information
|
|
57
|
-
refuse_section = soup.find("div", {"aria-labelledby": "refuseCollectionTitle"})
|
|
58
|
-
if refuse_section:
|
|
59
|
-
refuse_title = refuse_section.find(
|
|
60
|
-
"p", {"id": "refuseCollectionTitle"}
|
|
61
|
-
).text
|
|
62
|
-
refuse_next_collection = (
|
|
63
|
-
refuse_section.find(text=lambda text: "Next collection" in text)
|
|
64
|
-
.strip()
|
|
65
|
-
.split(": ")[1]
|
|
66
|
-
)
|
|
67
|
-
|
|
68
|
-
dict_data = {
|
|
69
|
-
"type": refuse_title,
|
|
70
|
-
"collectionDate": datetime.strptime(
|
|
71
|
-
refuse_next_collection, "%a, %d %B %Y"
|
|
72
|
-
).strftime("%d/%m/%Y"),
|
|
73
|
-
}
|
|
74
|
-
data["bins"].append(dict_data)
|
|
75
|
-
|
|
76
|
-
# Extract food waste collection information
|
|
77
|
-
food_section = soup.find(
|
|
78
|
-
"div", {"aria-labelledby": "domesticFoodCollectionTitle"}
|
|
79
|
-
)
|
|
80
|
-
if food_section:
|
|
81
|
-
food_title = food_section.find(
|
|
82
|
-
"p", {"id": "domesticFoodCollectionTitle"}
|
|
83
|
-
).text
|
|
84
|
-
food_next_collection = (
|
|
85
|
-
food_section.find(text=lambda text: "Next collection" in text)
|
|
86
|
-
.strip()
|
|
87
|
-
.split(": ")[1]
|
|
88
|
-
)
|
|
89
|
-
|
|
90
|
-
dict_data = {
|
|
91
|
-
"type": food_title,
|
|
92
|
-
"collectionDate": datetime.strptime(
|
|
93
|
-
food_next_collection, "%a, %d %B %Y"
|
|
94
|
-
).strftime("%d/%m/%Y"),
|
|
95
|
-
}
|
|
96
|
-
data["bins"].append(dict_data)
|
|
97
|
-
|
|
98
|
-
# Extract communal food waste collection information
|
|
99
|
-
comfood_section = soup.find(
|
|
100
|
-
"div", {"aria-labelledby": "communalFoodCollectionTitle"}
|
|
101
|
-
)
|
|
102
|
-
if comfood_section:
|
|
103
|
-
comfood_title = comfood_section.find(
|
|
104
|
-
"p", {"id": "communalFoodCollectionTitle"}
|
|
105
|
-
).text
|
|
106
|
-
comfood_next_collection = (
|
|
107
|
-
comfood_section.find(text=lambda text: "Next collection" in text)
|
|
108
|
-
.strip()
|
|
109
|
-
.split(": ")[1]
|
|
110
|
-
)
|
|
111
|
-
|
|
112
|
-
dict_data = {
|
|
113
|
-
"type": comfood_title,
|
|
114
|
-
"collectionDate": datetime.strptime(
|
|
115
|
-
comfood_next_collection, "%a, %d %B %Y"
|
|
116
|
-
).strftime("%d/%m/%Y"),
|
|
117
|
-
}
|
|
118
|
-
data["bins"].append(dict_data)
|
|
119
|
-
|
|
120
|
-
comrec_section = soup.find(
|
|
121
|
-
"div", {"aria-labelledby": "recyclingCommunalCollectionTitle"}
|
|
59
|
+
# Extract collection information for all bin types
|
|
60
|
+
section_ids = (
|
|
61
|
+
"recyclingCollectionTitle",
|
|
62
|
+
"refuseCollectionTitle",
|
|
63
|
+
"domesticFoodCollectionTitle",
|
|
64
|
+
"communalFoodCollectionTitle",
|
|
65
|
+
"recyclingCommunalCollectionTitle",
|
|
66
|
+
"refuseCommunalCollectionTitle",
|
|
122
67
|
)
|
|
123
|
-
if comrec_section:
|
|
124
|
-
comrec_title = comrec_section.find(
|
|
125
|
-
"p", {"id": "recyclingCommunalCollectionTitle"}
|
|
126
|
-
).text
|
|
127
|
-
comrec_next_collection = (
|
|
128
|
-
comrec_section.find(text=lambda text: "Next collection" in text)
|
|
129
|
-
.strip()
|
|
130
|
-
.split(": ")[1]
|
|
131
|
-
)
|
|
132
68
|
|
|
133
|
-
|
|
134
|
-
|
|
135
|
-
|
|
136
|
-
|
|
137
|
-
|
|
138
|
-
|
|
139
|
-
|
|
140
|
-
|
|
141
|
-
|
|
142
|
-
|
|
143
|
-
|
|
144
|
-
|
|
145
|
-
|
|
146
|
-
|
|
147
|
-
|
|
148
|
-
|
|
149
|
-
|
|
150
|
-
|
|
151
|
-
|
|
69
|
+
for section_id in section_ids:
|
|
70
|
+
section = soup.find("div", {"aria-labelledby": section_id})
|
|
71
|
+
if not section:
|
|
72
|
+
continue
|
|
73
|
+
|
|
74
|
+
title, next_collection = extract_collection_date(section, section_id)
|
|
75
|
+
if not (title and next_collection):
|
|
76
|
+
continue
|
|
77
|
+
|
|
78
|
+
try:
|
|
79
|
+
parsed = datetime.strptime(next_collection, "%a, %d %B %Y")
|
|
80
|
+
except ValueError:
|
|
81
|
+
continue
|
|
82
|
+
|
|
83
|
+
data["bins"].append(
|
|
84
|
+
{
|
|
85
|
+
"type": title,
|
|
86
|
+
"collectionDate": parsed.strftime("%d/%m/%Y"),
|
|
87
|
+
}
|
|
152
88
|
)
|
|
153
89
|
|
|
154
|
-
|
|
155
|
-
"type": comref_title,
|
|
156
|
-
"collectionDate": datetime.strptime(
|
|
157
|
-
comref_next_collection, "%a, %d %B %Y"
|
|
158
|
-
).strftime("%d/%m/%Y"),
|
|
159
|
-
}
|
|
160
|
-
data["bins"].append(dict_data)
|
|
161
|
-
|
|
162
|
-
return data
|
|
90
|
+
return data
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
2
|
Name: uk_bin_collection
|
|
3
|
-
Version: 0.159.
|
|
3
|
+
Version: 0.159.2
|
|
4
4
|
Summary: Python Lib to collect UK Bin Data
|
|
5
5
|
Author: Robert Bradley
|
|
6
6
|
Author-email: robbrad182@gmail.com
|
|
@@ -14,7 +14,7 @@ Requires-Dist: holidays
|
|
|
14
14
|
Requires-Dist: icalevents (>=0.2.1,<0.3.0)
|
|
15
15
|
Requires-Dist: lxml
|
|
16
16
|
Requires-Dist: pandas
|
|
17
|
-
Requires-Dist: pillow (>=10.0.0
|
|
17
|
+
Requires-Dist: pillow (>=10.0.0)
|
|
18
18
|
Requires-Dist: python-dateutil
|
|
19
19
|
Requires-Dist: requests
|
|
20
20
|
Requires-Dist: selenium
|
|
@@ -276,7 +276,7 @@ uk_bin_collection/uk_bin_collection/councils/SouthRibbleCouncil.py,sha256=juX7pg
|
|
|
276
276
|
uk_bin_collection/uk_bin_collection/councils/SouthStaffordshireDistrictCouncil.py,sha256=ACQMHWyamnj1ag3gNF-8Jhp-DKUok1GhFdnzH4nCzwU,3201
|
|
277
277
|
uk_bin_collection/uk_bin_collection/councils/SouthTynesideCouncil.py,sha256=dxXGrJfg_fn2IPTBgq6Duwy0WY8GYLafMuisaCjOnbs,3426
|
|
278
278
|
uk_bin_collection/uk_bin_collection/councils/SouthamptonCityCouncil.py,sha256=exNoI-Vun_C5FowCYhZ_600MBUe_OPR7MdGZEMNLL0I,1542
|
|
279
|
-
uk_bin_collection/uk_bin_collection/councils/SouthwarkCouncil.py,sha256=
|
|
279
|
+
uk_bin_collection/uk_bin_collection/councils/SouthwarkCouncil.py,sha256=AR4qv12oHkMRmNb62pk0IByeOQ7ePh-FnxrK4TWqM0E,2772
|
|
280
280
|
uk_bin_collection/uk_bin_collection/councils/SpelthorneBoroughCouncil.py,sha256=iamG0wxIyYprttJPVc0jdbOoHavc1AmRpMhyc02MUrE,5703
|
|
281
281
|
uk_bin_collection/uk_bin_collection/councils/StAlbansCityAndDistrictCouncil.py,sha256=mPZz6Za6kTSkrfHnj0OfwtnpRYR1dKvxbuFEKnWsiL8,1451
|
|
282
282
|
uk_bin_collection/uk_bin_collection/councils/StHelensBC.py,sha256=X9dvnQTNn7QUO8gv1A587e1aDI92TWN4iNLATTn3H3w,4777
|
|
@@ -350,8 +350,8 @@ uk_bin_collection/uk_bin_collection/councils/tests/test_south_kesteven_district_
|
|
|
350
350
|
uk_bin_collection/uk_bin_collection/councils/tests/test_south_kesteven_integration.py,sha256=ax_kevIIB1BpDTVjEnoiZnDk0srkc1Vw7B2i5XLLqiE,6647
|
|
351
351
|
uk_bin_collection/uk_bin_collection/create_new_council.py,sha256=m-IhmWmeWQlFsTZC4OxuFvtw5ZtB8EAJHxJTH4O59lQ,1536
|
|
352
352
|
uk_bin_collection/uk_bin_collection/get_bin_data.py,sha256=Qb76X46V0UMZJwO8zMNPvnVY7jNa-bmTlrirDi1tuJA,4553
|
|
353
|
-
uk_bin_collection-0.159.
|
|
354
|
-
uk_bin_collection-0.159.
|
|
355
|
-
uk_bin_collection-0.159.
|
|
356
|
-
uk_bin_collection-0.159.
|
|
357
|
-
uk_bin_collection-0.159.
|
|
353
|
+
uk_bin_collection-0.159.2.dist-info/LICENSE,sha256=vABBUOzcrgfaTKpzeo-si9YVEun6juDkndqA8RKdKGs,1071
|
|
354
|
+
uk_bin_collection-0.159.2.dist-info/METADATA,sha256=Qv0Q_mW-eoZiNsewU9DZrrkXKhvoGZ-GmTINNjFEo0U,26761
|
|
355
|
+
uk_bin_collection-0.159.2.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
|
|
356
|
+
uk_bin_collection-0.159.2.dist-info/entry_points.txt,sha256=36WCSGMWSc916S3Hi1ZkazzDKHaJ6CD-4fCEFm5MIao,90
|
|
357
|
+
uk_bin_collection-0.159.2.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|
{uk_bin_collection-0.159.0.dist-info → uk_bin_collection-0.159.2.dist-info}/entry_points.txt
RENAMED
|
File without changes
|