diff options
| author | Thibaut Horel <thibaut.horel@gmail.com> | 2014-10-24 12:16:51 -0400 |
|---|---|---|
| committer | Thibaut Horel <thibaut.horel@gmail.com> | 2014-10-24 12:16:51 -0400 |
| commit | ece1d828d53d6123fcecb5ea8bf9b126d1728ccc (patch) | |
| tree | b669382d0e5f1234556d1aeb7fa919891510b24d /facebook_scraping/seed.py | |
| parent | 7426d8ff0e7969eb1a86bdb5bec8a0c971309e2b (diff) | |
| download | fast-seeding-ece1d828d53d6123fcecb5ea8bf9b126d1728ccc.tar.gz | |
Add code
Diffstat (limited to 'facebook_scraping/seed.py')
| -rw-r--r-- | facebook_scraping/seed.py | 7 |
1 files changed, 7 insertions, 0 deletions
diff --git a/facebook_scraping/seed.py b/facebook_scraping/seed.py new file mode 100644 index 0000000..932c16b --- /dev/null +++ b/facebook_scraping/seed.py @@ -0,0 +1,7 @@ +import sys +from bs4 import BeautifulSoup + +soup = BeautifulSoup(open(sys.argv[1])) +links = [div.a["href"] for div in soup.findAll("div", class_="fsl")] +for link in links: + print link |