blob: 1103e605de27890e4f3896cb580a333bfa91d625 (
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
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
|
%global _empty_manifest_terminate_build 0
Name: python-PyWebScraper
Version: 0.1.5
Release: 1
Summary: A web scraper that combines both Beautiful Soup (bs4) and Selenium.
License: MIT License
URL: https://github.com/glowingkitty/PyWebScraper
Source0: https://mirrors.aliyun.com/pypi/web/packages/59/83/e2abdc5ea9f56d77b37dc8473b130799ddf117e6b63dc0360d4d3dff8592/PyWebScraper-0.1.5.tar.gz
BuildArch: noarch
Requires: python3-bs4
Requires: python3-requests
Requires: python3-selenium
%description
A web scraper that combines both Beautiful Soup (bs4) and Selenium.
Want to support the development and stay updated?
<a href="https://www.patreon.com/bePatron?u=24983231"><img alt="Become a Patreon" src="https://raw.githubusercontent.com/marcoEDU/PyWebScraper/master/images/patreon_button.svg"></a> <a href="https://liberapay.com/glowingkitty/donate"><img alt="Donate using Liberapay" src="https://liberapay.com/assets/widgets/donate.svg"></a>
## Installation
```
pip install PyWebScraper
```
## Usage
```
from PyWebScraper import Scraper
```
Scraper() will load bs4 or selenium (defined with the input 'scraper_type') to then load a website (defined by the input 'url') and save it under Scraper().page.
Optional inputs for Scraper():
```
url = str (will be opened in scraper and page saved in Scraper().page)
scraper_type = 'bs4' or 'selenium'
scroll_down = boolean (scrolls down in selenium first before saving page)
user_agent = 'desktop' or 'mobile'
auto_close_selenium = boolean (if False, you can further interact with the selenium browser via Scraper().selenium)
selenium_remote_webdriver = str (IP for a remote webdriver for selenium, see https://www.selenium.dev/docs/site/en/remote_webdriver/remote_webdriver_client/)
```
%package -n python3-PyWebScraper
Summary: A web scraper that combines both Beautiful Soup (bs4) and Selenium.
Provides: python-PyWebScraper
BuildRequires: python3-devel
BuildRequires: python3-setuptools
BuildRequires: python3-pip
%description -n python3-PyWebScraper
A web scraper that combines both Beautiful Soup (bs4) and Selenium.
Want to support the development and stay updated?
<a href="https://www.patreon.com/bePatron?u=24983231"><img alt="Become a Patreon" src="https://raw.githubusercontent.com/marcoEDU/PyWebScraper/master/images/patreon_button.svg"></a> <a href="https://liberapay.com/glowingkitty/donate"><img alt="Donate using Liberapay" src="https://liberapay.com/assets/widgets/donate.svg"></a>
## Installation
```
pip install PyWebScraper
```
## Usage
```
from PyWebScraper import Scraper
```
Scraper() will load bs4 or selenium (defined with the input 'scraper_type') to then load a website (defined by the input 'url') and save it under Scraper().page.
Optional inputs for Scraper():
```
url = str (will be opened in scraper and page saved in Scraper().page)
scraper_type = 'bs4' or 'selenium'
scroll_down = boolean (scrolls down in selenium first before saving page)
user_agent = 'desktop' or 'mobile'
auto_close_selenium = boolean (if False, you can further interact with the selenium browser via Scraper().selenium)
selenium_remote_webdriver = str (IP for a remote webdriver for selenium, see https://www.selenium.dev/docs/site/en/remote_webdriver/remote_webdriver_client/)
```
%package help
Summary: Development documents and examples for PyWebScraper
Provides: python3-PyWebScraper-doc
%description help
A web scraper that combines both Beautiful Soup (bs4) and Selenium.
Want to support the development and stay updated?
<a href="https://www.patreon.com/bePatron?u=24983231"><img alt="Become a Patreon" src="https://raw.githubusercontent.com/marcoEDU/PyWebScraper/master/images/patreon_button.svg"></a> <a href="https://liberapay.com/glowingkitty/donate"><img alt="Donate using Liberapay" src="https://liberapay.com/assets/widgets/donate.svg"></a>
## Installation
```
pip install PyWebScraper
```
## Usage
```
from PyWebScraper import Scraper
```
Scraper() will load bs4 or selenium (defined with the input 'scraper_type') to then load a website (defined by the input 'url') and save it under Scraper().page.
Optional inputs for Scraper():
```
url = str (will be opened in scraper and page saved in Scraper().page)
scraper_type = 'bs4' or 'selenium'
scroll_down = boolean (scrolls down in selenium first before saving page)
user_agent = 'desktop' or 'mobile'
auto_close_selenium = boolean (if False, you can further interact with the selenium browser via Scraper().selenium)
selenium_remote_webdriver = str (IP for a remote webdriver for selenium, see https://www.selenium.dev/docs/site/en/remote_webdriver/remote_webdriver_client/)
```
%prep
%autosetup -n PyWebScraper-0.1.5
%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-PyWebScraper -f filelist.lst
%dir %{python3_sitelib}/*
%files help -f doclist.lst
%{_docdir}/*
%changelog
* Tue Jun 20 2023 Python_Bot <Python_Bot@openeuler.org> - 0.1.5-1
- Package Spec generated
|
