blob: 5ecd02f4f636756b5f395fef38412f53486f98bf (
plain)
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
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
|
%global _empty_manifest_terminate_build 0
Name: python-recipe-scrapers
Version: 14.36.1
Release: 1
Summary: Python package, scraping recipes from all over the internet
License: MIT License
URL: https://github.com/hhursev/recipe-scrapers/
Source0: https://mirrors.nju.edu.cn/pypi/web/packages/99/a0/082537aaeeb21ea6feff914375c12feb9e09c02b441fc7724faa3411f7fb/recipe_scrapers-14.36.1.tar.gz
BuildArch: noarch
Requires: python3-beautifulsoup4
Requires: python3-extruct
Requires: python3-isodate
Requires: python3-requests
%description
A simple web scraping tool for recipe sites.
pip install recipe-scrapers
then:
from recipe_scrapers import scrape_me
scraper = scrape_me('https://www.allrecipes.com/recipe/158968/spinach-and-feta-turkey-burgers/')
# Q: What if the recipe site I want to extract information from is not listed below?
# A: You can give it a try with the wild_mode option! If there is Schema/Recipe available it will work just fine.
scraper = scrape_me('https://www.feastingathome.com/tomato-risotto/', wild_mode=True)
scraper.host()
scraper.title()
scraper.total_time()
scraper.image()
scraper.ingredients()
scraper.instructions()
scraper.instructions_list()
scraper.yields()
scraper.to_json()
scraper.links()
scraper.nutrients() # if available
You also have an option to scrape html-like content
import requests
from recipe_scrapers import scrape_html
url = "https://www.allrecipes.com/recipe/158968/spinach-and-feta-turkey-burgers/"
html = requests.get(url).content
scraper = scrape_html(html=html, org_url=url)
scraper.title()
scraper.total_time()
# etc...
Notes:
- ``scraper.links()`` returns a list of dictionaries containing all of the <a> tag attributes. The attribute names are the dictionary keys.
%package -n python3-recipe-scrapers
Summary: Python package, scraping recipes from all over the internet
Provides: python-recipe-scrapers
BuildRequires: python3-devel
BuildRequires: python3-setuptools
BuildRequires: python3-pip
%description -n python3-recipe-scrapers
A simple web scraping tool for recipe sites.
pip install recipe-scrapers
then:
from recipe_scrapers import scrape_me
scraper = scrape_me('https://www.allrecipes.com/recipe/158968/spinach-and-feta-turkey-burgers/')
# Q: What if the recipe site I want to extract information from is not listed below?
# A: You can give it a try with the wild_mode option! If there is Schema/Recipe available it will work just fine.
scraper = scrape_me('https://www.feastingathome.com/tomato-risotto/', wild_mode=True)
scraper.host()
scraper.title()
scraper.total_time()
scraper.image()
scraper.ingredients()
scraper.instructions()
scraper.instructions_list()
scraper.yields()
scraper.to_json()
scraper.links()
scraper.nutrients() # if available
You also have an option to scrape html-like content
import requests
from recipe_scrapers import scrape_html
url = "https://www.allrecipes.com/recipe/158968/spinach-and-feta-turkey-burgers/"
html = requests.get(url).content
scraper = scrape_html(html=html, org_url=url)
scraper.title()
scraper.total_time()
# etc...
Notes:
- ``scraper.links()`` returns a list of dictionaries containing all of the <a> tag attributes. The attribute names are the dictionary keys.
%package help
Summary: Development documents and examples for recipe-scrapers
Provides: python3-recipe-scrapers-doc
%description help
A simple web scraping tool for recipe sites.
pip install recipe-scrapers
then:
from recipe_scrapers import scrape_me
scraper = scrape_me('https://www.allrecipes.com/recipe/158968/spinach-and-feta-turkey-burgers/')
# Q: What if the recipe site I want to extract information from is not listed below?
# A: You can give it a try with the wild_mode option! If there is Schema/Recipe available it will work just fine.
scraper = scrape_me('https://www.feastingathome.com/tomato-risotto/', wild_mode=True)
scraper.host()
scraper.title()
scraper.total_time()
scraper.image()
scraper.ingredients()
scraper.instructions()
scraper.instructions_list()
scraper.yields()
scraper.to_json()
scraper.links()
scraper.nutrients() # if available
You also have an option to scrape html-like content
import requests
from recipe_scrapers import scrape_html
url = "https://www.allrecipes.com/recipe/158968/spinach-and-feta-turkey-burgers/"
html = requests.get(url).content
scraper = scrape_html(html=html, org_url=url)
scraper.title()
scraper.total_time()
# etc...
Notes:
- ``scraper.links()`` returns a list of dictionaries containing all of the <a> tag attributes. The attribute names are the dictionary keys.
%prep
%autosetup -n recipe-scrapers-14.36.1
%build
%py3_build
%install
%py3_install
install -d -m755 %{buildroot}/%{_pkgdocdir}
if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi
if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi
if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi
if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi
pushd %{buildroot}
if [ -d usr/lib ]; then
find usr/lib -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/lib64 ]; then
find usr/lib64 -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/bin ]; then
find usr/bin -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/sbin ]; then
find usr/sbin -type f -printf "/%h/%f\n" >> filelist.lst
fi
touch doclist.lst
if [ -d usr/share/man ]; then
find usr/share/man -type f -printf "/%h/%f.gz\n" >> doclist.lst
fi
popd
mv %{buildroot}/filelist.lst .
mv %{buildroot}/doclist.lst .
%files -n python3-recipe-scrapers -f filelist.lst
%dir %{python3_sitelib}/*
%files help -f doclist.lst
%{_docdir}/*
%changelog
* Wed May 10 2023 Python_Bot <Python_Bot@openeuler.org> - 14.36.1-1
- Package Spec generated
|
