Skip to content

Commit e450c2e

Browse files
committed
Update
1 parent 748a28f commit e450c2e

File tree

6 files changed

+113
-13
lines changed

6 files changed

+113
-13
lines changed

.vscode/settings.json

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
{
2+
"python.pythonPath": "/usr/bin/python"
3+
}

instapic.py

Lines changed: 49 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,49 @@
1+
#!/usr/bin/env python
2+
3+
## Instagram Post Image Downloader
4+
## Install Python pip Modules
5+
6+
# Python2 (pip)
7+
## pip install wget
8+
## pip install beautifulsoup4
9+
## pip install lxml
10+
11+
# Python3 (pip)
12+
## pip3 install wget
13+
## pip3 install beautifulsoup4
14+
## pip3 install lxml
15+
16+
from bs4 import BeautifulSoup
17+
import wget
18+
19+
try: #python3
20+
from urllib.request import urlopen
21+
except: #python2
22+
from urllib2 import urlopen
23+
input = raw_input
24+
25+
## User input
26+
url = input("\033[1;32mEnter a Instagram Post URL : \033[1;m")
27+
28+
insta_post = urlopen(url)
29+
bs = BeautifulSoup(insta_post , "lxml")
30+
31+
## Find Insta Post Image
32+
metatag = bs.find("meta", {"property": "og:image"})
33+
34+
if metatag is not None:
35+
36+
print (metatag["content"])
37+
print ("\n")
38+
39+
print ("Image Started Downloading.......")
40+
41+
## Download Image via Wget
42+
filename = wget.download(metatag["content"])
43+
print ("\n")
44+
45+
print ("Done")
46+
print ("\n")
47+
48+
else:
49+
print ("Error")
File renamed without changes.
File renamed without changes.

test/weblink.py

Lines changed: 19 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,19 @@
1+
#!/usr/bin/env python
2+
3+
from BeautifulSoup import BeautifulSoup
4+
#import urllib2
5+
import cfscrape
6+
import re
7+
8+
#html_page = urllib2.urlopen("https://example.com")
9+
10+
# Get the text at the set URL
11+
scraper = cfscrape.create_scraper()
12+
13+
url = "https://example.com"
14+
cfurl = scraper.get(url).content
15+
soup = BeautifulSoup(cfurl)
16+
for link in soup.findAll('a', attrs={'href': re.compile("^(http|https)://")}):
17+
18+
## Print Output
19+
print link.get('href')

weblink.py

Lines changed: 42 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -1,19 +1,48 @@
11
#!/usr/bin/env python
22

3-
from BeautifulSoup import BeautifulSoup
4-
#import urllib2
5-
import cfscrape
6-
import re
7-
8-
#html_page = urllib2.urlopen("https://example.com")
9-
10-
# Get the text at the set URL
11-
scraper = cfscrape.create_scraper()
3+
## Install Python pip Modules
4+
5+
# Python2 (pip)
6+
## pip install cfscrape
7+
## pip install beautifulsoup4
8+
## pip install lxml
9+
10+
# Python3 (pip)
11+
## pip3 install cfscrape
12+
## pip3 install beautifulsoup4
13+
## pip3 install lxml
14+
15+
#from bs4 import BeautifulSoup
16+
#import cfscrape
17+
#import re
18+
19+
import sys
1220

13-
url = "https://example.com"
21+
VER = 2
22+
23+
try:
24+
if sys.version_info >= (3,0):
25+
VER = 3
26+
from bs4 import BeautifulSoup
27+
import cfscrape
28+
import re
29+
else:
30+
input = raw_input
31+
from bs4 import BeautifulSoup
32+
import cfscrape
33+
import re
34+
except:
35+
pass
36+
37+
38+
## User input
39+
url = input("\033[1;32mEnter a URL : \033[1;m")
40+
41+
scraper = cfscrape.create_scraper()
1442
cfurl = scraper.get(url).content
15-
soup = BeautifulSoup(cfurl)
43+
soup = BeautifulSoup(cfurl, "lxml")
1644
for link in soup.findAll('a', attrs={'href': re.compile("^(http|https)://")}):
1745

18-
## Print Output
19-
print link.get('href')
46+
urls = link.get("href")
47+
print (urls)
48+

0 commit comments

Comments
 (0)