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
|
"""根据搜索词下载百度图片"""
import re
import sys
import urllib
import os
import requests
def getPage(keyword,page,n):
page=page*n
keyword=urllib.parse.quote(keyword, safe='/')
url_begin= "http://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word="
url = url_begin+ keyword + "&pn=" +str(page) + "&gsm="+str(hex(page))+"&ct=&ic=0&lm=-1&width=0&height=0"
return url
def get_onepage_urls(onepageurl):
try:
html = requests.get(onepageurl).text
except Exception as e:
print(e)
pic_urls = []
return pic_urls
pic_urls = re.findall('"objURL":"(.*?)",', html, re.S)
return pic_urls
def down_pic(pic_urls, keyword):
"""给出图片链接列表, 下载所有图片"""
for i, pic_url in enumerate(pic_urls):
try:
pic = requests.get(pic_url, timeout=15)
string =str(i + 1) + '.jpg'
if os.path.exists('./' + keyword):
with open('./' + keyword + '/' + string, 'wb') as f:
f.write(pic.content)
print('成功下载第%s张图片: %s' % (str(i + 1), str(pic_url)))
else:
os.mkdir('./' + keyword)
with open('./' + keyword + '/' + string, 'wb') as f:
f.write(pic.content)
print('成功下载第%s张图片: %s' % (str(i + 1), str(pic_url)))
except Exception as e:
print('下载第%s张图片时失败: %s' % (str(i + 1), str(pic_url)))
print(e)
continue
if __name__ == '__main__':
keyword = '天海翼'
page_begin=0
page_number=30
image_number=3
all_pic_urls = []
while 1:
if page_begin>image_number:
break
print("第%d次请求数据",[page_begin])
url=getPage(keyword,page_begin,page_number)
onepage_urls= get_onepage_urls(url)
page_begin += 1
all_pic_urls.extend(onepage_urls)
down_pic(list(set(all_pic_urls)), keyword)
|