0x2620/python-ox
2
1
Fork 0
Code Issues Pull requests Releases Wiki Activity

more raw regexp strings

Browse source
This commit is contained in:
j 2024-08-30 13:30:47 +02:00
commit ae10c5c9b9
11 changed files with 45 additions and 45 deletions
Download patch file Download diff file Expand all files Collapse all files

20
ox/web/wikipedia.py
View file

@ -81,36 +81,36 @@ def get_movie_data(wikipedia_url):
if 'amg_id' in filmbox and not filmbox['amg_id'].isdigit():
del filmbox['amg_id']
if 'Allmovie movie' in data:
filmbox['amg_id'] = find_re(data, 'Allmovie movie\|.*?(\d+)')
filmbox['amg_id'] = find_re(data, r'Allmovie movie\|.*?(\d+)')
elif 'Allmovie title' in data:
filmbox['amg_id'] = find_re(data, 'Allmovie title\|.*?(\d+)')
filmbox['amg_id'] = find_re(data, r'Allmovie title\|.*?(\d+)')
if 'Official website' in data:
filmbox['website'] = find_re(data, 'Official website\|(.*?)}').strip()
filmbox['website'] = find_re(data, r'Official website\|(.*?)}').strip()
r = re.compile('{{IMDb title\|id=(\d{7})', re.IGNORECASE).findall(data)
r = re.compile(r'{{IMDb title\|id=(\d{7})', re.IGNORECASE).findall(data)
if r:
filmbox['imdb_id'] = r[0]
else:
r = re.compile('{{IMDb title\|(\d{7})', re.IGNORECASE).findall(data)
r = re.compile(r'{{IMDb title\|(\d{7})', re.IGNORECASE).findall(data)
if r:
filmbox['imdb_id'] = r[0]
r = re.compile('{{Internet Archive.*?\|id=(.*?)[\|}]', re.IGNORECASE).findall(data)
r = re.compile(r'{{Internet Archive.*?\|id=(.*?)[\|}]', re.IGNORECASE).findall(data)
if r:
filmbox['archiveorg_id'] = r[0]
r = re.compile('{{mojo title\|(.*?)[\|}]', re.IGNORECASE).findall(data)
r = re.compile(r'{{mojo title\|(.*?)[\|}]', re.IGNORECASE).findall(data)
if r:
filmbox['mojo_id'] = r[0].replace('id=', '')
r = re.compile('{{rotten-tomatoes\|(.*?)[\|}]', re.IGNORECASE).findall(data)
r = re.compile(r'{{rotten-tomatoes\|(.*?)[\|}]', re.IGNORECASE).findall(data)
if r:
filmbox['rottentomatoes_id'] = r[0].replace('id=', '')
if 'google video' in data:
filmbox['google_video_id'] = find_re(data, 'google video\|.*?(\d*?)[\|}]')
filmbox['google_video_id'] = find_re(data, r'google video\|.*?(\d*?)[\|}]')
if 'DEFAULTSORT' in data:
filmbox['title_sort'] = find_re(data, '''\{\{DEFAULTSORT:(.*?)\}\}''')
filmbox['title_sort'] = find_re(data, r'''\{\{DEFAULTSORT:(.*?)\}\}''')
return filmbox
def get_image_url(name):