blob: 4e17b30b0658d84fa083198cccd9de9b6b295e96 (
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
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
|
%global _empty_manifest_terminate_build 0
Name: python-scrapfly-sdk
Version: 0.8.6
Release: 1
Summary: Scrapfly SDK for Scrapfly
License: BSD
URL: https://github.com/scrapfly/python-sdk
Source0: https://mirrors.aliyun.com/pypi/web/packages/f3/7c/a9f781012e8ed997e585945bf2812a4bad56b628e994d24493f9b4799145/scrapfly-sdk-0.8.6.tar.gz
BuildArch: noarch
Requires: python3-decorator
Requires: python3-requests
Requires: python3-dateutil
Requires: python3-loguru
Requires: python3-urllib3
Requires: python3-backoff
Requires: python3-soupsieve
Requires: python3-brotlipy
Requires: python3-cchardet
Requires: python3-msgpack
Requires: python3-lxml
Requires: python3-beautifulsoup4
Requires: python3-scrapy
Requires: python3-extruct
Requires: python3-bumpversion
Requires: python3-isort
Requires: python3-readme-renderer
Requires: python3-twine
Requires: python3-setuptools
Requires: python3-wheel
Requires: python3-pdoc3
Requires: python3-lxml
Requires: python3-beautifulsoup4
Requires: python3-soupsieve
Requires: python3-extruct
Requires: python3-scrapy
Requires: python3-brotlipy
Requires: python3-cchardet
Requires: python3-msgpack
%description
# Scrapfly SDK
## Installation
`pip install scrapfly-sdk`
You can also install extra dependencies
* `pip install "scrapfly-sdk[seepdup]"` for performance improvement
* `pip install "scrapfly-sdk[concurrency]"` for concurrency out of the box (asyncio / thread)
* `pip install "scrapfly-sdk[scrapy]"` for scrapy integration
* `pip install "scrapfly-sdk[scrapy]"` Everything!
## Get Your API Key
You can create a free account on [Scrapfly](https://scrapfly.io/register) to get your API Key.
* [Usage](https://scrapfly.io/docs/sdk/python)
* [Python API](https://scrapfly.github.io/python-scrapfly/scrapfly)
* [Open API 3 Spec](https://scrapfly.io/docs/openapi#get-/scrape)
* [Scrapy Integration](https://scrapfly.io/docs/sdk/scrapy)
## Migration
### Migrate from 0.7.x to 0.8
asyncio-pool dependency has been dropped
`scrapfly.concurrent_scrape` is now an async generator. If the concurrency is `None` or not defined, the max concurrency allowed by
your current subscription is used.
```python
async for result in scrapfly.concurrent_scrape(concurrency=10, scrape_configs=[ScrapConfig(...), ...]):
print(result)
```
brotli args is deprecated and will be removed in the next minor. There is not benefit in most of case
versus gzip regarding and size and use more CPU.
### What's new
### 0.8.x
* Better error log
* Async/Improvement for concurrent scrape with asyncio
* Scrapy media pipeline are now supported out of the box
%package -n python3-scrapfly-sdk
Summary: Scrapfly SDK for Scrapfly
Provides: python-scrapfly-sdk
BuildRequires: python3-devel
BuildRequires: python3-setuptools
BuildRequires: python3-pip
%description -n python3-scrapfly-sdk
# Scrapfly SDK
## Installation
`pip install scrapfly-sdk`
You can also install extra dependencies
* `pip install "scrapfly-sdk[seepdup]"` for performance improvement
* `pip install "scrapfly-sdk[concurrency]"` for concurrency out of the box (asyncio / thread)
* `pip install "scrapfly-sdk[scrapy]"` for scrapy integration
* `pip install "scrapfly-sdk[scrapy]"` Everything!
## Get Your API Key
You can create a free account on [Scrapfly](https://scrapfly.io/register) to get your API Key.
* [Usage](https://scrapfly.io/docs/sdk/python)
* [Python API](https://scrapfly.github.io/python-scrapfly/scrapfly)
* [Open API 3 Spec](https://scrapfly.io/docs/openapi#get-/scrape)
* [Scrapy Integration](https://scrapfly.io/docs/sdk/scrapy)
## Migration
### Migrate from 0.7.x to 0.8
asyncio-pool dependency has been dropped
`scrapfly.concurrent_scrape` is now an async generator. If the concurrency is `None` or not defined, the max concurrency allowed by
your current subscription is used.
```python
async for result in scrapfly.concurrent_scrape(concurrency=10, scrape_configs=[ScrapConfig(...), ...]):
print(result)
```
brotli args is deprecated and will be removed in the next minor. There is not benefit in most of case
versus gzip regarding and size and use more CPU.
### What's new
### 0.8.x
* Better error log
* Async/Improvement for concurrent scrape with asyncio
* Scrapy media pipeline are now supported out of the box
%package help
Summary: Development documents and examples for scrapfly-sdk
Provides: python3-scrapfly-sdk-doc
%description help
# Scrapfly SDK
## Installation
`pip install scrapfly-sdk`
You can also install extra dependencies
* `pip install "scrapfly-sdk[seepdup]"` for performance improvement
* `pip install "scrapfly-sdk[concurrency]"` for concurrency out of the box (asyncio / thread)
* `pip install "scrapfly-sdk[scrapy]"` for scrapy integration
* `pip install "scrapfly-sdk[scrapy]"` Everything!
## Get Your API Key
You can create a free account on [Scrapfly](https://scrapfly.io/register) to get your API Key.
* [Usage](https://scrapfly.io/docs/sdk/python)
* [Python API](https://scrapfly.github.io/python-scrapfly/scrapfly)
* [Open API 3 Spec](https://scrapfly.io/docs/openapi#get-/scrape)
* [Scrapy Integration](https://scrapfly.io/docs/sdk/scrapy)
## Migration
### Migrate from 0.7.x to 0.8
asyncio-pool dependency has been dropped
`scrapfly.concurrent_scrape` is now an async generator. If the concurrency is `None` or not defined, the max concurrency allowed by
your current subscription is used.
```python
async for result in scrapfly.concurrent_scrape(concurrency=10, scrape_configs=[ScrapConfig(...), ...]):
print(result)
```
brotli args is deprecated and will be removed in the next minor. There is not benefit in most of case
versus gzip regarding and size and use more CPU.
### What's new
### 0.8.x
* Better error log
* Async/Improvement for concurrent scrape with asyncio
* Scrapy media pipeline are now supported out of the box
%prep
%autosetup -n scrapfly-sdk-0.8.6
%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-scrapfly-sdk -f filelist.lst
%dir %{python3_sitelib}/*
%files help -f doclist.lst
%{_docdir}/*
%changelog
* Tue Jun 20 2023 Python_Bot <Python_Bot@openeuler.org> - 0.8.6-1
- Package Spec generated
|
