/
h_category_thread.py
200 lines (169 loc) · 6.29 KB
/
h_category_thread.py
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
#!/usr/bin/env python
# -*- coding: latin-1 -*-
# -*- coding: iso-8859-15 -*-
# -*- coding: ascii -*-
# -*- coding: utf-8 -*-
import proxy_module
from bs4 import BeautifulSoup
import re
import sys
import image_proxy
import MySQLdb
import os
import csv
import threading
import time
import logging
import firebug_proxy
from pyvirtualdisplay import Display
import br_hand
import br_image
logging.basicConfig(level=logging.DEBUG,format='%(asctime)s (%(threadName)-2s) %(message)s',)
def in_file(data):
with open('h_category2.csv', 'ab+') as csvfile:
spamwriter = csv.writer(csvfile)
spamwriter.writerow(data)
csvfile.close()
def image_finder(soup,movie_name,movie_link):
data = soup.select('a[href="%s"]'%movie_link)
image_link = data[0].img["src"].encode("ascii","ignore")
start = image_link.find("img")
image_link = "http://"+image_link[start:]
#image_proxy.image("achieves_dir",image_link,movie_name)
filename = "achieves_dir2/"+movie_name
#br = br_image.main(image_link,filename)
try:
obj = br_hand.machanize_handler()
br = obj.set_proxy()
br.retrieve(image_link,filename)
br.close()
except:
pass
return image_link
def catodaily(cat_name,cat_link,movie_name,movie_link,watch,watch_link,image_link):
#page,driver= firebug_proxy.main(watch_link)
page= proxy_module.main(watch_link)
soup = BeautifulSoup(page)
page.close()
#driver.close()
if soup.find_all("iframe",attrs={"src":re.compile("dailymotion")}):
em = soup.find_all("iframe",attrs={"src":re.compile("dailymotion")})
em_link = em[0]["src"].encode("ascii","ignore")
elif soup.find_all("embed",attrs={"src":re.compile(r"dailymotion")}):
em = soup.find_all("embed",attrs={"src":re.compile(r"dailymotion")})
em_link = em[0]["src"].encode("ascii","ignore")
else:
em_link = " on this link: " +watch_link.encode("ascii","ignore")
collection = [cat_name,cat_link,movie_name,movie_link,"Daliymotion",watch,em_link,image_link]
logging.debug(tuple(collection))
in_file(collection)
def catoyou(cat_name,cat_link,movie_name,movie_link,watch,watch_link,image_link):
#page,driver= firebug_proxy.main(watch_link)
page= proxy_module.main(watch_link)
soup = BeautifulSoup(page)
page.close()
#driver.close()
if soup.find_all("iframe",attrs={"src":re.compile("youtube")}):
em = soup.find_all("iframe",attrs={"src":re.compile("youtube")})
em_link = em[0]["src"].encode("ascii","ignore")
elif soup.find_all("embed",attrs={"src":re.compile(r"youtube")}):
em = soup.find_all("embed",attrs={"src":re.compile(r"youtube")})
em_link = em[0]["src"].encode("ascii","ignore")
else:
em_link = " on this link: " +watch_link.encode("ascii","ignore")
collection = [cat_name,cat_link,movie_name,movie_link,"youtube",watch,em_link,image_link]
logging.debug(tuple(collection))
in_file(collection)
def cato3(cat_name,cat_link,movie_name,movie_link):
page = proxy_module.main(movie_link)
soup = BeautifulSoup(page)
image_link=image_finder(soup,movie_name,movie_link)
page.close()
data = soup.find_all("strong")
threads = []
for l in data:
s = l.get_text().encode("ascii","ignore")
if re.search(r"Dailymotion",s):
para = l.find_next("p")
soup2 = BeautifulSoup(str(para))
data2 = soup2.find_all("a")
for m in data2:
watch = m.get_text().encode("ascii","ignore")
watch_link = m.get("href").encode("ascii","ignore")
arg =(cat_name,cat_link,movie_name,movie_link,watch,watch_link,image_link)
t = threading.Thread(target=catodaily,args=arg)
threads.append(t)
t.start()
logging.debug("Dailymotion")
if len(threads)>5:
t.join()
del threads[:]
elif re.search(r"Youtube",s):
para = l.find_next("p")
soup2 = BeautifulSoup(str(para))
data2 = soup2.find_all("a")
for m in data2:
watch = m.get_text().encode("ascii","ignore")
watch_link = m.get("href").encode("ascii","ignore")
arg =(cat_name,cat_link,movie_name,movie_link,watch,watch_link,image_link)
t = threading.Thread(target=catoyou,args=arg)
threads.append(t)
t.start()
logging.debug("Youtube")
if len(threads)>10:
t.join()
del threads[:]
else:
pass
def cato2(cat_name,cat_link):
page = proxy_module.main(cat_link)
soup = BeautifulSoup(page)
page.close()
data = soup.find_all("div",attrs={"class":"results_content"})
threads = []
for l in data:
movie_name = l.a.get_text().encode("ascii","ignore")
movie_link = l.a.get("href").encode("ascii","ignore")
#cato3(cat_name,cat_link,movie_name,movie_link)
t = threading.Thread(target=cato3,args=(cat_name,cat_link,movie_name,movie_link))
threads.append(t)
t.start()
logging.debug("cato2")
if len(threads)>10:
t.join()
del threads[:]
def cato():
link = "http://www.hindilinks4u.net/"
page = proxy_module.main(link)
soup = BeautifulSoup(page)
page.close()
data = soup.find_all("h2",attrs={"class":"widgettitle"})
for l in data:
if str(l.get_text()).strip() =="Categories":
cat_list = l.find_next("ul")
soup = BeautifulSoup(str(cat_list))
data = soup.find_all("a")
threads = []
for l in data:
cat_name= l.get_text().encode("ascii","ignore")
cat_link= l.get("href").encode("ascii","ignore")
#cato2(cat_name,cat_link)
t = threading.Thread(target=cato2,args=(cat_name,cat_link))
threads.append(t)
t.start()
logging.debug("cato")
if len(threads)>10:
t.join()
del threads[:]
if __name__=="__main__":
try:
os.mkdir("achieves_dir2")
except:
pass
try:
os.mkdir("h_category_dir")
except:
pass
collection =["cat_name","cat_link","movie_name","movie_link","type","watch","em_link","image_link"]
in_file(collection)
cato()