/
director.py
157 lines (127 loc) · 5.56 KB
/
director.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
#!/usr/bin/env python
import proxy_module
from bs4 import BeautifulSoup
import re
import firebug_proxy
import sys
import image_proxy
import MySQLdb
import os
def image_finder(soup,movie_name,movie_link):
#print movie_link
try:
data = soup.select('a[href="%s"]'%movie_link)
image_link = data[0].img["src"].encode("ascii","ignore")
image_proxy.image("achieves_dir",image_link,movie_name)
return image_link
except:
return " image not get for: "+movie_link
def directoryou(db,cursor,links,director_name, director_link,movie_name,movie_link,watch,watch_link,image_link):
page = proxy_module.main(watch_link)
soup = BeautifulSoup(page)
page.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")
print
print
#print director_name, director_link,movie_name,movie_link,watch,watch_link
#print director_name,movie_name,watch,em_link
sql = """insert ignore into director(diector,director_link,movie,movie_link,watch,watch_link,image_link) values("%s","%s","%s","%s","%s","%s","%s")"""%(director_name,director_link,movie_name,movie_link,watch,em_link,image_link)
print sql
cursor.execute(sql)
db.commit()
def directordaily(db,cursor,links,director_name, director_link,movie_name,movie_link,watch,watch_link,image_link):
page = proxy_module.main(watch_link)
soup = BeautifulSoup(page)
page.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")
print
#print director_name, director_link,movie_name,movie_link,watch,watch_link
#print director_name,director_link,movie_name,watch,em_link
sql = """insert ignore into director(diector,director_link,movie,movie_link,watch,watch_link,image_link) values("%s","%s","%s","%s","%s","%s","%s")"""%(director_name,director_link,movie_name,movie_link,watch,em_link,image_link)
print sql
cursor.execute(sql)
db.commit()
def director4(db,cursor,links,director_name, director_link,movie_name,movie_link):
page = proxy_module.main(movie_link)
soup = BeautifulSoup(page)
page.close()
image_link=image_finder(soup,movie_name,movie_link)
data = soup.find_all("strong")
for l in data:
s = l.get_text().encode("ascii","ignore")
if re.search(r"Dailymotion",s):
print
print "Dailymotion"
para = l.find_next("p")
soup2 = BeautifulSoup(str(para))
data2 = soup2.find_all("a")
for m in data2:
#print m.get_text(),m.get("href") ok here
watch = m.get_text().encode("ascii","ignore")
watch_link = m.get("href").encode("ascii","ignore")
directordaily(db,cursor,links,director_name, director_link,movie_name,movie_link,watch,watch_link,image_link)
#sys.exit()
elif re.search(r"Youtube",s):
print
print "You tube"
para = l.find_next("p")
soup2 = BeautifulSoup(str(para))
data2 = soup2.find_all("a")
for m in data2:
#print m.get_text(),m.get("href") ok here
watch = m.get_text().encode("ascii","ignore")
watch_link = m.get("href").encode("ascii","ignore")
directoryou(db,cursor,links,director_name, director_link,movie_name,movie_link,watch,watch_link,image_link)
#sys.exit()
else:
pass
def director3(db,cursor,links,director_name, director_link):
page = proxy_module.main(director_link)
soup = BeautifulSoup(page)
page.close()
data = soup.find_all("div",attrs={"class":"results_content"})
for l in data:
movie_link = l.a.get("href").encode("ascii","ignore")
movie_name = l.a.get_text().encode("ascii","ignore")
director4(db,cursor,links,director_name, director_link,movie_name,movie_link)
def director2(db,cursor,links):
soup = BeautifulSoup(links)
data = soup.find_all("a")
for l in data:
director_name = l.get_text().encode("ascii","ignore")
director_link = l.get("href").encode("ascii","ignore")
#print director_name,director_link
director3(db,cursor,links,director_name, director_link)
def director(db,cursor):
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() =="Movies By Directors":
links = l.find_next("ul")
director2(db,cursor,str(links))
if __name__=="__main__":
try:
os.mkdir("director_dir")
except:
pass
db = MySQLdb.connect("localhost","root","india123","hindi_link")
cursor = db.cursor()
director(db, cursor)
db.close()