bpmcdevitt/stritch_wolves_college_stats
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

download html works!

Browse source
This commit is contained in:
Brendan McDevitt 2017-08-02 17:19:19 -04:00
parent e6fc19ca0d
commit 9832e77ba3
1 changed files with 9 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
pull_box_score.py
View file

@ -1,7 +1,7 @@
#!/usr/bin/env python #!/usr/bin/env python
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
import requests import requests, urllib, os
#### FIRST THREE YEARS 2010/2011/2012 ARE DIFFERENT WAYS TO RETRIEVE THAN 13-17 #### FIRST THREE YEARS 2010/2011/2012 ARE DIFFERENT WAYS TO RETRIEVE THAN 13-17
@ -41,6 +41,13 @@ class Old_Stats:
link_list.append('http://' + self.base_urls()[url_step].replace(self.sport_url, '') + '/' + link.get('href')) link_list.append('http://' + self.base_urls()[url_step].replace(self.sport_url, '') + '/' + link.get('href'))
return link_list return link_list
def download_html_links(self):
for url_step in range(0, len(self.get_box_score_links()) + 1):
filename = 'box_score' + str(url_step) + '.htm'
response = requests.get(self.get_box_score_links()[url_step])
with open('./data/' + filename, "wb") as code:
code.write(response.content)
old_stats = Old_Stats() old_stats = Old_Stats()
print old_stats.get_box_score_links() old_stats.download_html_links()