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

imdb cleanups

Browse source
This commit is contained in:
j 2009-11-30 01:46:56 +01:00
parent 4e38581c51
commit 80641b5461
1 changed files with 15 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
oxweb/imdb.py
View file

@ -75,8 +75,8 @@ def getRawMovieData(imdbId):
data['release date'] = getMovieReleaseDate(imdbId) data['release date'] = getMovieReleaseDate(imdbId)
return data return data
def getMovieInfo(imdbId): def getMovieInfo(imdbId, timeout=-1):
data = readUrlUnicode(getUrlBase(imdbId)) data = readUrlUnicode(getUrlBase(imdbId), timeout=timeout)
info = dict() info = dict()
info['poster'] = findRe(data, 'name="poster".*?<img .*?src="(.*?)"') info['poster'] = findRe(data, 'name="poster".*?<img .*?src="(.*?)"')
if info['poster'] and '_V' in info['poster']: if info['poster'] and '_V' in info['poster']:
@ -84,7 +84,12 @@ def getMovieInfo(imdbId):
for i in re.compile('<h5>(.*?):</h5>(.*?)<div class="info"', re.DOTALL).findall(data): for i in re.compile('<h5>(.*?):</h5>(.*?)<div class="info"', re.DOTALL).findall(data):
title = stripTags(i[0]).strip().lower() title = stripTags(i[0]).strip().lower()
txt= stripTags(i[1]).strip() if title in ('genre', ):
txt = i[1].split('</div>')[0]
else:
txt= i[1]
txt = stripTags(txt).strip()
def cleanUp(k): def cleanUp(k):
k = decodeHtml(k).replace(u'\xa0', ' ').strip() k = decodeHtml(k).replace(u'\xa0', ' ').strip()
if k.endswith('more'): k=k[:-len('more')].strip() if k.endswith('more'): k=k[:-len('more')].strip()
@ -258,7 +263,7 @@ def creditList(data, section=None):
credits_ = re.compile('''<tr>.*?<td valign="top">(.*?)</td><td.*?</td><td valign="top">(.*?)</td></tr>''').findall(data) credits_ = re.compile('''<tr>.*?<td valign="top">(.*?)</td><td.*?</td><td valign="top">(.*?)</td></tr>''').findall(data)
credits = [] credits = []
for c_ in credits_: for c_ in credits_:
c = [decodeHtml(c_[0]).strip(), decodeHtml(c_[1]).strip()] c = [stripTags(decodeHtml(c_[0]).strip()), stripTags(decodeHtml(c_[1]).strip())]
if section=='writers': if section=='writers':
c[1] = c[1].replace('<br>', '').strip().replace(')', '').replace('(','') c[1] = c[1].replace('<br>', '').strip().replace(')', '').replace('(','')
if c[1].endswith(' and'): c[1] = c[1][:-4] if c[1].endswith(' and'): c[1] = c[1][:-4]
@ -328,6 +333,7 @@ def getMovieLocations(imdbId):
url = "%slocations" % getUrlBase(imdbId) url = "%slocations" % getUrlBase(imdbId)
data = readUrlUnicode(url) data = readUrlUnicode(url)
locations = re.compile('<dt><a href="/List.*?>(.*?)</a></dt>').findall(data) locations = re.compile('<dt><a href="/List.*?>(.*?)</a></dt>').findall(data)
locations = [decodeHtml(l) for l in locations]
return locations return locations
def getMovieImages(imdbId, keys=('still_frame', 'poster', 'product')): def getMovieImages(imdbId, keys=('still_frame', 'poster', 'product')):
@ -366,6 +372,8 @@ def getMovieTrivia(imdbId):
t = t.replace(u'”', '"') t = t.replace(u'”', '"')
if t.endswith('<br><br>'): if t.endswith('<br><br>'):
t = t[:-8] t = t[:-8]
if t.endswith('<br>\n<br>'):
t = t[:-len('<br>\n<br>')]
return t.strip() return t.strip()
trivia = [clean(t) for t in trivia] trivia = [clean(t) for t in trivia]
return trivia return trivia
@ -454,7 +462,9 @@ def getMovieBusinessSum(imdbId):
b_['budget'] = int(intValue(budget[0].replace(',', ''))) b_['budget'] = int(intValue(budget[0].replace(',', '')))
if 'gross' in business: if 'gross' in business:
b_['gross'] = int(intValue(business['gross'][0].replace(',', ''))) gross = filter(lambda x: x.startswith('$'), business['gross'])
if gross:
b_['gross'] = int(intValue(gross[0].replace(',', '')))
#b_['gross'] = sum([int(intValue(i.replace(',', ''))) for i in business['gross']]) #b_['gross'] = sum([int(intValue(i.replace(',', ''))) for i in business['gross']])
#if 'weekend gross' in business: #if 'weekend gross' in business:
# b_['gross'] += sum([int(intValue(i.replace(',', ''))) for i in business['weekend gross']]) # b_['gross'] += sum([int(intValue(i.replace(',', ''))) for i in business['weekend gross']])