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
| import requests
import re
import time
import hashlib
def get_page(url):
print('GET %s' %url)
try:
response=requests.get(url)
if response.status_code == 200:
return response.content
except Exception:
pass
def parse_index(res):
obj=re.compile('class="items.*?<a href="(.*?)"',re.S)
detail_urls=obj.findall(res.decode('gbk'))
for detail_url in detail_urls:
if not detail_url.startswith('http'):
detail_url='http://www.xiaohuar.com'+detail_url
yield detail_url
def parse_detail(res):
obj=re.compile('id="media".*?src="(.*?)"',re.S)
res=obj.findall(res.decode('gbk'))
if len(res) > 0:
movie_url=res[0]
return movie_url
def save(movie_url):
response=requests.get(movie_url,stream=False)
if response.status_code == 200:
m=hashlib.md5()
m.update(('%s%s.mp4' %(movie_url,time.time())).encode('utf-8'))
filename=m.hexdigest()
with open(r'./movies/%s.mp4' %filename,'wb') as f:
f.write(response.content)
f.flush()
def main():
index_url='http://www.xiaohuar.com/list-3-{0}.html'
for i in range(5):
print('*'*50,i)
index_page=get_page(index_url.format(i,))
detail_urls=parse_index(index_page)
for detail_url in detail_urls:
detail_page=get_page(detail_url)
movie_url=parse_detail(detail_page)
if movie_url:
save(movie_url)
if __name__ == '__main__':
main()
from concurrent.futures import ThreadPoolExecutor
import queue
import requests
import re
import time
import hashlib
from threading import current_thread
p=ThreadPoolExecutor(50)
def get_page(url):
print('%s GET %s' %(current_thread().getName(),url))
try:
response=requests.get(url)
if response.status_code == 200:
return response.content
except Exception as e:
print(e)
def parse_index(res):
print('%s parse index ' %current_thread().getName())
res=res.result()
obj=re.compile('class="items.*?<a href="(.*?)"',re.S)
detail_urls=obj.findall(res.decode('gbk'))
for detail_url in detail_urls:
if not detail_url.startswith('http'):
detail_url='http://www.xiaohuar.com'+detail_url
p.submit(get_page,detail_url).add_done_callback(parse_detail)
def parse_detail(res):
print('%s parse detail ' %current_thread().getName())
res=res.result()
obj=re.compile('id="media".*?src="(.*?)"',re.S)
res=obj.findall(res.decode('gbk'))
if len(res) > 0:
movie_url=res[0]
print('MOVIE_URL: ',movie_url)
with open('db.txt','a') as f:
f.write('%s\n' %movie_url)
p.submit(save,movie_url)
print('%s下载任务已经提交' %movie_url)
def save(movie_url):
print('%s SAVE: %s' %(current_thread().getName(),movie_url))
try:
response=requests.get(movie_url,stream=False)
if response.status_code == 200:
m=hashlib.md5()
m.update(('%s%s.mp4' %(movie_url,time.time())).encode('utf-8'))
filename=m.hexdigest()
with open(r'./movies/%s.mp4' %filename,'wb') as f:
f.write(response.content)
f.flush()
except Exception as e:
print(e)
def main():
index_url='http://www.xiaohuar.com/list-3-{0}.html'
for i in range(5):
p.submit(get_page,index_url.format(i,)).add_done_callback(parse_index)
if __name__ == '__main__':
main()
|
