Download as
Browse Code »

Commit a761547424c098689a27b48addd30d2a53dfecc9

Authored by Gustavo Bernardo
1 parent 49b84075
Exists in master and in 5 other branches amadeus_univasf, dev, image-crop, pdf_file_html, refactoring

removed comments

Showing 1 changed file with 1 additions and 4 deletions   Show diff stats
links/image-crawler.py
  Diff comments   View file @a761547
1 -'''  
2 from bs4 import BeautifulSoup 1 from bs4 import BeautifulSoup
3 from urllib.request import urlopen 2 from urllib.request import urlopen
4 import urllib.request 3 import urllib.request
@@ -40,7 +39,7 @@ def get_images(url): @@ -40,7 +39,7 @@ def get_images(url):
40 each = each[0:pos+4] 39 each = each[0:pos+4]
41 if not booleano: 40 if not booleano:
42 continue 41 continue
43 - 42 +
44 if each[0] + each[1] == '//' or each[0] == '/': 43 if each[0] + each[1] == '//' or each[0] == '/':
45 each = 'http:'+each 44 each = 'http:'+each
46 if each[0:4] != 'http' and each[0:5] != 'https': 45 if each[0:4] != 'http' and each[0:5] != 'https':
@@ -52,5 +51,3 @@ def get_images(url): @@ -52,5 +51,3 @@ def get_images(url):
52 urllib.request.urlretrieve(each,"%s"%(caminho)+str(contador)+filename) 51 urllib.request.urlretrieve(each,"%s"%(caminho)+str(contador)+filename)
53 except Exception: 52 except Exception:
54 continue 53 continue
55 -  
56 -'''