Last active
September 29, 2016 21:28
-
-
Save Joshuacourse/15435f57f1acf5ffd970406cb5ffc3dd to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
### Scraping using package "Beautiful Soup" from Python | |
### Scrape the links for every countries and store the data in a txt file called "record3.txt" | |
f = open('record.txt', 'r') # 'r' for read | |
lines3 = f.readlines() | |
f.close() | |
for i in range(len(lines3)): | |
url="http://www.alexa.com/siteinfo/" + lines3[i] | |
text = requests.get(url).text | |
soup = BeautifulSoup(text) | |
TT=soup.find("span",{"data-cat":"countryRank"}).find("a").get_text() | |
f4 = open('record3.txt', 'a') | |
f4.write(TT+"\n") | |
f4.close() | |
f2 = open('record1.txt', 'r') # 'r' for read | |
lines = f2.readlines() | |
f2.close() | |
print lines | |
## "http://www.alexa.com" + lines[1].strip() | |
f3 = open('record2.txt', 'r') # 'r' for read | |
lines2 = f3.readlines() | |
f3.close() | |
### Create an empty dictionary "M" for the storage of the Top-500 websites for each country | |
M=OrderedDict() | |
print lines2 | |
for country in lines2: | |
M[country.strip()]=[] | |
print M | |
### export the dictionary "M" as json file | |
import json | |
json_str = json.dumps(M) | |
print(M) | |
f = open('Site.json', 'wb') | |
f.write(json_str) | |
f.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment