0x2620/python-oxweb
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

getWikiData should not only work for en.wikipedia.org, newline can be before or after delimiter, use elif, parse google video

Browse source
This commit is contained in:
j 2009-07-11 18:30:16 +02:00
parent af15fd01a0
commit 928e6a4769
1 changed files with 10 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
oxweb/wikipedia.py
View file

@ -37,8 +37,9 @@ def getUrlByAllmovieId(allmovieId):
return '' return ''
def getWikiData(wikipediaUrl): def getWikiData(wikipediaUrl):
title = wikipediaUrl.replace('http://en.wikipedia.org/wiki/', '') url = wikipediaUrl.replace('wikipedia.org/wiki/', 'wikipedia.org/w/index.php?title=')
url = "http://en.wikipedia.org/w/index.php?title=%s&action=raw" % title url = "%s&action=raw" % url
print url
data = getUrlUnicode(url) data = getUrlUnicode(url)
return data return data
@ -46,7 +47,10 @@ def getMovieData(wikipediaUrl):
data = getWikiData(wikipediaUrl) data = getWikiData(wikipediaUrl)
filmbox_data = findRe(data, '''\{\{Infobox.Film(.*?)\n\}\}''') filmbox_data = findRe(data, '''\{\{Infobox.Film(.*?)\n\}\}''')
filmbox = {} filmbox = {}
for row in filmbox_data.strip().split('\n|'): _box = filmbox_data.strip().split('\n|')
if len(_box) == 1:
_box = _box[0].split('|\n')
for row in _box:
d = row.split('=') d = row.split('=')
if len(d) == 2: if len(d) == 2:
key = d[0].strip() key = d[0].strip()
@ -56,7 +60,7 @@ def getMovieData(wikipediaUrl):
filmbox[key] = value filmbox[key] = value
if 'imdb title' in data: if 'imdb title' in data:
filmbox['imdb_id'] = findRe(data, 'imdb title\|.*?(\d*?)\|') filmbox['imdb_id'] = findRe(data, 'imdb title\|.*?(\d*?)\|')
else if 'imdb episode' in data: elif 'imdb episode' in data:
filmbox['imdb_id'] = findRe(data, 'imdb episode\|.*?(\d*?)\|') filmbox['imdb_id'] = findRe(data, 'imdb episode\|.*?(\d*?)\|')
if 'Amg movie' in data: if 'Amg movie' in data:
filmbox['amg_id'] = findRe(data, 'Amg movie\|.*?(\d*?)\|') filmbox['amg_id'] = findRe(data, 'Amg movie\|.*?(\d*?)\|')
@ -64,6 +68,8 @@ def getMovieData(wikipediaUrl):
filmbox['rottentomatoes_id'] = findRe(data, 'rotten-tomatoes\|id\=(.*?)\|') filmbox['rottentomatoes_id'] = findRe(data, 'rotten-tomatoes\|id\=(.*?)\|')
if not filmbox['rottentomatoes_id']: if not filmbox['rottentomatoes_id']:
filmbox['rottentomatoes_id'] = findRe(data, 'rotten-tomatoes\|(.*?)\|') filmbox['rottentomatoes_id'] = findRe(data, 'rotten-tomatoes\|(.*?)\|')
if 'google video' in data:
filmbox['google_video_id'] = findRe(data, 'google video\|.*?(\d*?)\|')
if 'DEFAULTSORT' in data: if 'DEFAULTSORT' in data:
filmbox['title_sort'] = findRe(data, '''\{\{DEFAULTSORT:(.*?)\}\}''') filmbox['title_sort'] = findRe(data, '''\{\{DEFAULTSORT:(.*?)\}\}''')
return filmbox return filmbox