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
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
|
%global _empty_manifest_terminate_build 0
Name: python-BaiduImagesDownload
Version: 2.0.0
Release: 1
Summary: download image from Baidu Image
License: MIT
URL: https://github.com/YXL76/BaiduImagesDownload
Source0: https://mirrors.aliyun.com/pypi/web/packages/d2/89/356b6d76558ceeac7add69a0669ee8cd4bdc795a7fd0965b3dd9983961ca/BaiduImagesDownload-2.0.0.tar.gz
BuildArch: noarch
Requires: python3-aiodns
Requires: python3-aiohttp
Requires: python3-cchardet
Requires: python3-tqdm
%description
# BaiduImagesDownload
[](https://github.com/YXL76/BaiduImagesDownload/actions)
[](https://codecov.io/gh/YXL76/BaiduImagesDownload)
[](https://www.codacy.com/manual/YXL76/BaiduImagesDownload?utm_source=github.com&utm_medium=referral&utm_content=YXL76/BaiduImagesDownload&utm_campaign=Badge_Grade)
> `BaiduImagesDownload`是一个快速、简单百度图片爬取工具
```python
from BaiduImagesDownload import Crawler
net, num, urls = Crawler.get_images_url('二次元', 20)
Crawler.download_images(urls)
```
目录
- [BaiduImagesDownload](#baiduimagesdownload)
- [安装](#安装)
- [使用](#使用)
- [基本](#基本)
- [下载设置](#下载设置)
- [文档](#文档)
- [get_images_url](#get_images_url)
- [download_images](#download_images)
- [日志](#日志)
- [许可](#许可)
## 安装
```bash
pip install BaiduImagesDownload
```
## 使用
### 基本
```python
from BaiduImagesDownload import Crawler
# original为True代表优先下载原图
net, num, urls = Crawler.get_images_url('二次元', 20, original=True)
Crawler.download_images(urls)
```
### 下载设置
```python
from BaiduImagesDownload import Crawler
# rule设置允许的图片格式，默认为('.png', '.jpg')
# timeout为超时时间，默认为60(s)
net, num, urls = Crawler.get_images_url('二次元', 20)
Crawler.download_images(urls, rule=('.png', '.jpg'), timeout=60)
```
## 文档
### get_images_url
```python
class Crawler:
@staticmethod
def get_images_url(word: str, num: int, original: bool = True,
timeout: int = __CONCURRENT_TIMEOUT) -> (bool, bool, list):
```
参数
- `word: str`: 搜索关键词
- `num: int`: 搜索数量
- `original： bool, optional`：是否下原图，默认为`True`
- `timeout: int, optional`: 请求 timeout, 默认为`60(s)`
返回
- `net: bool`: 网络连接是否成功，成功为 True，失败为 False
- `num: bool`: 图片数量是否满足，满足为 True，不足为 False
- `urls: list`: 获取的 urls，每项为一个`dict`，其中有两个键`obj_url`，`from_url`。`obj_url`为对应图片的`url`，`from_url`为`Referer`
### download_images
```python
class Crawler:
@staticmethod
def download_images(urls: list, rule: tuple = ('.png', '.jpg'),
path: str = 'download', timeout: int = __CONCURRENT_TIMEOUT,
concurrent: int = __CONCURRENT_NUM, command: bool = True) -> (int, int):
```
参数
- `urls: list`: 需要爬的图片列表，格式与`get_images_url`返回的相同
- `rule: tuple, optional`: 允许下载的格式，默认为`('.png', '.jpg')`
- `path: str, optional`: 图片下载的路径，默认为`'download'`
- `timeout: int, optional`: 请求 timeout, 默认为`60(s)`
- `concurrent: int, optional`: 并行下载的数量，默认为`100`
- `command: bool, optional`: 是否在控制台显示进度条，默认为`True`
返回
- `success: int`: 下载成功的数量
- `failed: int`: 下载失败的数量
### 日志
可以设置日志的等级以及输出，具体请查看[logging](https://docs.python.org/3.8/library/logging.html)
```python
import logging
from BaiduImagesDownload import logger
# 设置日志的等级为DEBUG
# 默认为INFO
logger.setLevel(logging.DEBUG)
# 设置输出到文件
file_handler = logging.FileHandler('~/BaiduImagesDownload.log')
file_handler.setFormatter(logging.Formatter(
'[%(asctime)s] [%(levelname)s] %(message)s')) # 设置输出格式
logger.addHandler(file_handler)
```
## 许可
[](https://github.com/YXL76/BaiduImagesDownload/blob/master/LICENSE)
%package -n python3-BaiduImagesDownload
Summary: download image from Baidu Image
Provides: python-BaiduImagesDownload
BuildRequires: python3-devel
BuildRequires: python3-setuptools
BuildRequires: python3-pip
%description -n python3-BaiduImagesDownload
# BaiduImagesDownload
[](https://github.com/YXL76/BaiduImagesDownload/actions)
[](https://codecov.io/gh/YXL76/BaiduImagesDownload)
[](https://www.codacy.com/manual/YXL76/BaiduImagesDownload?utm_source=github.com&utm_medium=referral&utm_content=YXL76/BaiduImagesDownload&utm_campaign=Badge_Grade)
> `BaiduImagesDownload`是一个快速、简单百度图片爬取工具
```python
from BaiduImagesDownload import Crawler
net, num, urls = Crawler.get_images_url('二次元', 20)
Crawler.download_images(urls)
```
目录
- [BaiduImagesDownload](#baiduimagesdownload)
- [安装](#安装)
- [使用](#使用)
- [基本](#基本)
- [下载设置](#下载设置)
- [文档](#文档)
- [get_images_url](#get_images_url)
- [download_images](#download_images)
- [日志](#日志)
- [许可](#许可)
## 安装
```bash
pip install BaiduImagesDownload
```
## 使用
### 基本
```python
from BaiduImagesDownload import Crawler
# original为True代表优先下载原图
net, num, urls = Crawler.get_images_url('二次元', 20, original=True)
Crawler.download_images(urls)
```
### 下载设置
```python
from BaiduImagesDownload import Crawler
# rule设置允许的图片格式，默认为('.png', '.jpg')
# timeout为超时时间，默认为60(s)
net, num, urls = Crawler.get_images_url('二次元', 20)
Crawler.download_images(urls, rule=('.png', '.jpg'), timeout=60)
```
## 文档
### get_images_url
```python
class Crawler:
@staticmethod
def get_images_url(word: str, num: int, original: bool = True,
timeout: int = __CONCURRENT_TIMEOUT) -> (bool, bool, list):
```
参数
- `word: str`: 搜索关键词
- `num: int`: 搜索数量
- `original： bool, optional`：是否下原图，默认为`True`
- `timeout: int, optional`: 请求 timeout, 默认为`60(s)`
返回
- `net: bool`: 网络连接是否成功，成功为 True，失败为 False
- `num: bool`: 图片数量是否满足，满足为 True，不足为 False
- `urls: list`: 获取的 urls，每项为一个`dict`，其中有两个键`obj_url`，`from_url`。`obj_url`为对应图片的`url`，`from_url`为`Referer`
### download_images
```python
class Crawler:
@staticmethod
def download_images(urls: list, rule: tuple = ('.png', '.jpg'),
path: str = 'download', timeout: int = __CONCURRENT_TIMEOUT,
concurrent: int = __CONCURRENT_NUM, command: bool = True) -> (int, int):
```
参数
- `urls: list`: 需要爬的图片列表，格式与`get_images_url`返回的相同
- `rule: tuple, optional`: 允许下载的格式，默认为`('.png', '.jpg')`
- `path: str, optional`: 图片下载的路径，默认为`'download'`
- `timeout: int, optional`: 请求 timeout, 默认为`60(s)`
- `concurrent: int, optional`: 并行下载的数量，默认为`100`
- `command: bool, optional`: 是否在控制台显示进度条，默认为`True`
返回
- `success: int`: 下载成功的数量
- `failed: int`: 下载失败的数量
### 日志
可以设置日志的等级以及输出，具体请查看[logging](https://docs.python.org/3.8/library/logging.html)
```python
import logging
from BaiduImagesDownload import logger
# 设置日志的等级为DEBUG
# 默认为INFO
logger.setLevel(logging.DEBUG)
# 设置输出到文件
file_handler = logging.FileHandler('~/BaiduImagesDownload.log')
file_handler.setFormatter(logging.Formatter(
'[%(asctime)s] [%(levelname)s] %(message)s')) # 设置输出格式
logger.addHandler(file_handler)
```
## 许可
[](https://github.com/YXL76/BaiduImagesDownload/blob/master/LICENSE)
%package help
Summary: Development documents and examples for BaiduImagesDownload
Provides: python3-BaiduImagesDownload-doc
%description help
# BaiduImagesDownload
[](https://github.com/YXL76/BaiduImagesDownload/actions)
[](https://codecov.io/gh/YXL76/BaiduImagesDownload)
[](https://www.codacy.com/manual/YXL76/BaiduImagesDownload?utm_source=github.com&utm_medium=referral&utm_content=YXL76/BaiduImagesDownload&utm_campaign=Badge_Grade)
> `BaiduImagesDownload`是一个快速、简单百度图片爬取工具
```python
from BaiduImagesDownload import Crawler
net, num, urls = Crawler.get_images_url('二次元', 20)
Crawler.download_images(urls)
```
目录
- [BaiduImagesDownload](#baiduimagesdownload)
- [安装](#安装)
- [使用](#使用)
- [基本](#基本)
- [下载设置](#下载设置)
- [文档](#文档)
- [get_images_url](#get_images_url)
- [download_images](#download_images)
- [日志](#日志)
- [许可](#许可)
## 安装
```bash
pip install BaiduImagesDownload
```
## 使用
### 基本
```python
from BaiduImagesDownload import Crawler
# original为True代表优先下载原图
net, num, urls = Crawler.get_images_url('二次元', 20, original=True)
Crawler.download_images(urls)
```
### 下载设置
```python
from BaiduImagesDownload import Crawler
# rule设置允许的图片格式，默认为('.png', '.jpg')
# timeout为超时时间，默认为60(s)
net, num, urls = Crawler.get_images_url('二次元', 20)
Crawler.download_images(urls, rule=('.png', '.jpg'), timeout=60)
```
## 文档
### get_images_url
```python
class Crawler:
@staticmethod
def get_images_url(word: str, num: int, original: bool = True,
timeout: int = __CONCURRENT_TIMEOUT) -> (bool, bool, list):
```
参数
- `word: str`: 搜索关键词
- `num: int`: 搜索数量
- `original： bool, optional`：是否下原图，默认为`True`
- `timeout: int, optional`: 请求 timeout, 默认为`60(s)`
返回
- `net: bool`: 网络连接是否成功，成功为 True，失败为 False
- `num: bool`: 图片数量是否满足，满足为 True，不足为 False
- `urls: list`: 获取的 urls，每项为一个`dict`，其中有两个键`obj_url`，`from_url`。`obj_url`为对应图片的`url`，`from_url`为`Referer`
### download_images
```python
class Crawler:
@staticmethod
def download_images(urls: list, rule: tuple = ('.png', '.jpg'),
path: str = 'download', timeout: int = __CONCURRENT_TIMEOUT,
concurrent: int = __CONCURRENT_NUM, command: bool = True) -> (int, int):
```
参数
- `urls: list`: 需要爬的图片列表，格式与`get_images_url`返回的相同
- `rule: tuple, optional`: 允许下载的格式，默认为`('.png', '.jpg')`
- `path: str, optional`: 图片下载的路径，默认为`'download'`
- `timeout: int, optional`: 请求 timeout, 默认为`60(s)`
- `concurrent: int, optional`: 并行下载的数量，默认为`100`
- `command: bool, optional`: 是否在控制台显示进度条，默认为`True`
返回
- `success: int`: 下载成功的数量
- `failed: int`: 下载失败的数量
### 日志
可以设置日志的等级以及输出，具体请查看[logging](https://docs.python.org/3.8/library/logging.html)
```python
import logging
from BaiduImagesDownload import logger
# 设置日志的等级为DEBUG
# 默认为INFO
logger.setLevel(logging.DEBUG)
# 设置输出到文件
file_handler = logging.FileHandler('~/BaiduImagesDownload.log')
file_handler.setFormatter(logging.Formatter(
'[%(asctime)s] [%(levelname)s] %(message)s')) # 设置输出格式
logger.addHandler(file_handler)
```
## 许可
[](https://github.com/YXL76/BaiduImagesDownload/blob/master/LICENSE)
%prep
%autosetup -n BaiduImagesDownload-2.0.0
%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-BaiduImagesDownload -f filelist.lst
%dir %{python3_sitelib}/*
%files help -f doclist.lst
%{_docdir}/*
%changelog
* Fri Jun 09 2023 Python_Bot <Python_Bot@openeuler.org> - 2.0.0-1
- Package Spec generated
|
