jprdonnelly/congress
1
0
Fork 0
mirror of https://github.com/unitedstates/congress.git synced 2026-03-25 05:00:04 -04:00
Code Issues Packages Projects Releases Wiki Activity

fixed string vs. byte object in committee_meetings file when updating to python3

Browse Source
This commit is contained in:
stevesdawg
2020-10-04 17:37:59 -04:00
parent 3d26afdddc
commit 7118d88da9
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tasks/committee_meetings.py
View File

@@ -176,7 +176,7 @@ def fetch_house_committee_meetings(committees, options):
# Scrape the committee listing page for a list of committees with scrapable events.
committee_html = utils.download("http://docs.house.gov/Committee/Committees.aspx", "committee_schedule/house_overview.html", opts)
for cmte in re.findall(r'<option value="(....)">', committee_html):
for cmte in re.findall(r'<option value="(....)">', committee_html.decode('utf-8')):
if cmte not in committees:
logging.error("Invalid committee code: " + cmte)
continue
@@ -189,7 +189,7 @@ def fetch_house_committee_meetings(committees, options):
opts)
# It's not really valid?
html = html.replace("&nbsp;", " ") # who likes nbsp's? convert to spaces. but otherwise, entity is not recognized.
html = html.replace(b"&nbsp;", b" ") # who likes nbsp's? convert to spaces. but otherwise, entity is not recognized.
#print(html)
# Parse and loop through the meetings listed in the committee feed.
dom = lxml.etree.fromstring(html)