Skip to content

Commit

Permalink
[UK] 2024 standing down list.
Browse files Browse the repository at this point in the history
  • Loading branch information
dracos committed May 24, 2024
1 parent c2bc679 commit a08fc81
Show file tree
Hide file tree
Showing 3 changed files with 126 additions and 10 deletions.
15 changes: 7 additions & 8 deletions members/wikipedia-standingdown.py
Original file line number Diff line number Diff line change
Expand Up @@ -13,19 +13,18 @@
sys.path.append("../pyscraper")
from resolvemembernames import memberList

today = '2010-04-12'
today = '2024-05-24'

page = open('../rawdata/MPs_standing_down_in_2010').read()
page = open('../rawdata/Members_of_the_2024_standing_down').read()
page = re.sub('(?s)^.*?<caption>Members of Parliament not standing for re-election', '', page)
page = re.sub('(?s)</table>.*', '', page)

print('''<?xml version="1.0" encoding="ISO-8859-1"?>
<publicwhip>''')
m = re.findall('<li><a href="([^"]*)"[^>]*>([^<]*)</a>', page)
m = re.findall(r'<tr>\s*<td>.*?<a href="([^"]*)"[^>]*>([^<]*)</a>', page)
for row in m:
url, name = row
name = name.decode('utf-8')
if name in ('Iris Robinson', 'Ashok Kumar', 'David Taylor'): continue
id, canonname, canoncons = memberList.matchfullnamecons(name, None, today)
pid = memberList.membertoperson(id)
print((' <personinfo id="%s" name="%s" standing_down="1" />' % (pid, name)).encode('iso-8859-1'))
pid, canonname, canoncons = memberList.matchfullnamecons(name, None, today)
print((' <personinfo id="%s" name="%s" standing_down="1" />' % (pid, name)))
print('</publicwhip>')

117 changes: 117 additions & 0 deletions members/wikipedia-standingdown.xml
Original file line number Diff line number Diff line change
@@ -0,0 +1,117 @@
<?xml version="1.0" encoding="ISO-8859-1"?>
<publicwhip>
<personinfo id="uk.org.publicwhip/person/25531" name="Douglas Ross" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24742" name="Alex Cunningham" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10281" name="Margaret Hodge" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10534" name="Barry Sheerman" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10260" name="Harriet Harman" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10630" name="Alan Whitehead" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/11461" name="Charles Walker" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10061" name="Ben Bradshaw" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10842" name="Wayne David" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24943" name="Paul Blomfield" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10648" name="Rosie Winterton" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10031" name="Margaret Beckett" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10051" name="Crispin Blunt" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/11626" name="Mike Penning" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/11929" name="Adam Afriyie" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10828" name="Jon Cruddas" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25319" name="Colleen Fletcher" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24832" name="Andrew Percy" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/11323" name="Hywel Williams" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24691" name="Chloe Smith" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25360" name="William Wragg" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10575" name="Gary Streeter" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25815" name="Dehenna Davison" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24854" name="Sajid Javid" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24880" name="Mark Pawsey" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24773" name="Matt Hancock" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24933" name="George Eustice" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/14128" name="Edward Timpson" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25882" name="Jo Gideon" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10041" name="Paul Beresford" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24888" name="Stephen McPartland" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24862" name="Robin Walker" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10062" name="Graham Brady" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24821" name="Pauline Latham" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24828" name="Gordon Henderson" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24944" name="Craig Whittaker" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25834" name="Nicola Richards" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24802" name="Henry Smith" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/14131" name="John Howell" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/11804" name="Robert Goodwill" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25388" name="Julian Knight" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10854" name="Jonathan Djanogly" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24955" name="Matthew Offord" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25423" name="Conor McGinn" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25674" name="Alister Jack" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10707" name="Richard Bacon" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24815" name="Dominic Raab" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/11696" name="Philip Dunne" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25349" name="Margaret Greenwood" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25884" name="Andy Carter" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10292" name="George Howarth" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25361" name="Ian Blackford" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24910" name="Caroline Lucas" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25403" name="Will Quince" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25345" name="Royston Smith" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10095" name="Bill Cash" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25337" name="Lucy Allan" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25273" name="Peter Grant" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25295" name="Angela Crawley" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24901" name="Steve Brine" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25305" name="Douglas Chapman" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25825" name="Chris Clarkson" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/11026" name="Greg Knight" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/11973" name="Stewart Hosie" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25269" name="Mhairi Black" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25271" name="John McNally" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/11668" name="Ben Wallace" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25318" name="Philippa Whitford" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25600" name="Trudy Harrison" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/11927" name="Stephen Hammond" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/11506" name="David Jones" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24902" name="Alok Sharma" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10920" name="Chris Grayling" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25276" name="Lisa Cameron" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10715" name="John Baron" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25299" name="Patrick Grady" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10225" name="Nick Gibb" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24907" name="Bob Stewart" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/11785" name="James Duddridge" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10069" name="Nick Brown" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10075" name="Karen Buck" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10267" name="Oliver Heald" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24934" name="Mike Freer" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25332" name="Christina Rees" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/13736" name="Bob Neill" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24770" name="Kwasi Kwarteng" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25817" name="Nickie Aiken" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24871" name="Tracey Crouch" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/13836" name="Francie Molloy" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25883" name="Kieran Mullan" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/13893" name="Mickey Brady" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24919" name="Ian Mearns" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25331" name="Paul Scully" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10426" name="Theresa May" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24879" name="Brandon Lewis" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25438" name="James Heappey" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24784" name="Robert Halfon" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10371" name="Tim Loughton" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24804" name="Mark Menzies" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24756" name="Dan Poulter" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25831" name="Natalie Elphicke" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24822" name="Nadhim Zahawi" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24841" name="Chris Heaton-Harris" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10172" name="Jeffrey Donaldson" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25434" name="Holly Lynch" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24805" name="Yvonne Fovargue" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25812" name="James Grundy" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25408" name="Jo Churchill" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10348" name="Eleanor Laing" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10913" name="Michelle Gildernew" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/25426" name="Huw Merriman" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/11003" name="Kevan Jones" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/24866" name="Michael Ellis" standing_down="1" />
<personinfo id="uk.org.publicwhip/person/10499" name="John Redwood" standing_down="1" />
</publicwhip>
4 changes: 2 additions & 2 deletions scripts/weeklyupdate
Original file line number Diff line number Diff line change
Expand Up @@ -36,12 +36,12 @@ curl -s "https://en.wikipedia.org/wiki/3rd_Scottish_Parliament" > Members_of_the
curl -s "https://en.wikipedia.org/wiki/4th_Scottish_Parliament" > Members_of_the_4th_Scottish_Parliament
curl -s "https://en.wikipedia.org/wiki/5th_Scottish_Parliament" > Members_of_the_5th_Scottish_Parliament
curl -s "https://en.wikipedia.org/wiki/6th_Scottish_Parliament" > Members_of_the_6th_Scottish_Parliament
# curl -s "https://en.wikipedia.org/wiki/MPs_standing_down_in_the_United_Kingdom_general_election,_2010" > MPs_standing_down_in_2010
curl -s "https://en.wikipedia.org/wiki/2024_United_Kingdom_general_election" > Members_of_the_2024_standing_down
#svn -q commit -m "Weekly rawdata scrape commit"
cd ~/parlparse/members
./wikipedia-lords.py > wikipedia-lords.xml
./wikipedia-commons.py > wikipedia-commons.xml
# ./wikipedia-standingdown.py > wikipedia-standingdown.xml
./wikipedia-standingdown.py > wikipedia-standingdown.xml
# ./bbcconv.py > bbc-links.xml
cd ~/parlparse/pyscraper
ni/wikipedia-mla.py > ../members/wikipedia-mla.xml
Expand Down

0 comments on commit a08fc81

Please sign in to comment.