1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
|
Index: src/helpers/imdb.py
===================================================================
--- src/helpers/imdb.py (revision 11608)
+++ src/helpers/imdb.py (working copy)
@@ -53,19 +53,19 @@
parser = OptionParser(version='%prog 1.0', conflict_handler='resolve', usage="""
Search IMDB for a movie or a TV show
-freevo imdb [options] <search> [<output> <video file> [<video file>]]
+freevo imdb [options] | [<result> <fxd file> <video file> [<video file>]]
-Generate <output>.fxd for the movie. Files is a list of files that belongs to
-this movie. Use [dvd|vcd] to add the whole disc or use [dvd|vcd][title] to add
-a special DVD or VCD title to the list of files""")
+Generate a fxd for the movie. Files is a list of files that belongs to this
+movie. Use [dvd|vcd] to add the whole disc or use [dvd|vcd][title] to add a
+special DVD or VCD title to the list of files""")
parser.add_option('-v', '--verbose', action='count', default=0,
help='set the level of verbosity [default:%default]')
parser.add_option('-s', '--search', action='store_true', dest='search', default=False,
help='search imdb for string [default:%default]')
parser.add_option('-g', '--guess', action='store_true', dest='guess', default=False,
help='search imdb for possible filename match [default:%default]')
- parser.add_option('--tv', action='store_true', dest='tv', default=False,
- help='specify the search is a tv programme [default:%default]')
+ parser.add_option('--tv', action='store', dest='tv', default=None,
+ help='specify the id of a tv programme for a eipsode search [default:%default]')
parser.add_option('--season', dest='season', default=None,
help='specify the season in the search [default:%default]')
parser.add_option('--episode', dest='episode', default=None,
@@ -116,7 +116,9 @@
sys.exit(u'--search requires <search pattern>')
elif opts.guess and len(args) < 1:
sys.exit(u'--guess requires <guess pattern>')
- tv_marker = (opts.tv or opts.season or opts.episode) and '"' or ''
+ #elif opts.tv and len(args) < 1:
+ # sys.exit(u'--tv requires <imdb id>')
+ tv_marker = (opts.season or opts.episode) and '"' or ''
if opts.rom_drive is not None:
driveset = True
@@ -176,6 +178,23 @@
print '%s' % title.encode(opts.encoding)
sys.exit(0)
+ if opts.tv:
+ print "Searching IMDB for '%s' season:%s episode:%s..." % (opts.tv, opts.season, opts.episode)
+ results = fxd.getIMDBid(opts.tv, opts.season, opts.episode)
+ if len(results) == 0:
+ print 'No results'
+ #for result in results:
+ # if result[3]:
+ # title = 'http://www.imdb.com/title/tt%s/ %s %s (%s) %s' % (result[:1] + result[:4])
+ # elif result[2]:
+ # title = 'http://www.imdb.com/title/tt%s/ %s %s (%s)' % (result[:1] + result[:3])
+ # else:
+ # title = 'http://www.imdb.com/title/tt%s/ %s %s' % (result[:1] + result[:2])
+ # title = results
+ title = 'http://www.imdb.com/title/tt%s/ %s' % (results, results)
+ print '%s' % title.encode(opts.encoding)
+ sys.exit(0)
+
# normal usage
if len(args) < 3:
sys.exit(u'requires <imdb id> <fxd filename> <video file>|<cd id>')
Index: src/util/fxdimdb.py
===================================================================
--- src/util/fxdimdb.py (revision 11608)
+++ src/util/fxdimdb.py (working copy)
@@ -48,8 +48,15 @@
import codecs
import os
import traceback
-from BeautifulSoup import BeautifulSoup, NavigableString
-import HTMLParser
+from pprint import pprint, pformat
+try:
+ from html5lib import HTMLParser, treebuilders
+ from html5lib.treebuilders.soup import NavigableString
+ using_html5lib = True
+except ImportError:
+ import HTMLParser
+ from BeautifulSoup import BeautifulSoup, BeautifulStoneSoup, NavigableString
+ using_html5lib = False
import config
import util
@@ -232,6 +239,7 @@
response.close()
_debug_('id_list has %s items' % (len(self.id_list)))
+ #print 'id_list=%s' % (pformat(self.id_list))
if len(self.id_list) > 20:
# too many results, check if there are stupid results in the list
words = []
@@ -311,7 +319,11 @@
dvd = 0
try:
- soup = BeautifulSoup(results.read(), convertEntities='xml')
+ if using_html5lib:
+ parser = HTMLParser(tree=treebuilders.getTreeBuilder('beautifulsoup'))
+ soup = parser.parse(results.read())
+ else:
+ soup = BeautifulSoup(results.read(), convertEntities=BeautifulStoneSoup.HTML_ENTITIES)
except UnicodeDecodeError:
print "Unicode error: check that /usr/lib/python2.x/site.py has the correct default encoding"
traceback.print_exc()
@@ -336,68 +348,61 @@
self.info['year'] = y[1:-1]
except (AttributeError, TypeError, ValueError):
self.info['title'] = self.title
- self.info['year'] = title.find('a').string.strip()
+ try:
+ self.info['year'] = title.find('a').contents[0].strip()
+ except AttributeError:
+ self.info['year'] = ''
# Find the <div> with class info, each <h5> under this provides info
+ wanted_keys = ('release_date', 'genre', 'tagline', 'plot', 'plot_keywords',
+ 'also_known_as', 'mpaa', 'runtime', 'country', 'language',
+ 'color', 'aspect_ratio', 'sound_mix', 'certification',
+ )
+
for info in main.findAll('div', {'class' : 'info'}):
infoh5 = info.find('h5')
if not infoh5:
continue
try:
- infostr = infoh5.next
- key = infostr.string.strip(':').lower().replace(' ', '_')
- nextsibling = nextsibling = infoh5.nextSibling.strip()
- sections = info.findAll('a', { 'href' : re.compile('/Sections') })
- lists = info.findAll('a', { 'href' : re.compile('/List') })
- if len(nextsibling) > 0:
- self.info[key] = nextsibling
+ infostr = infoh5.find(text=True)
+ key = infostr.strip().strip(':').lower().replace(' ', '_')
+ if key not in wanted_keys:
+ continue
+ content = info.find('div', {'class' : 'info-content'})
+ infocontent = content.find(text=True)
+ if infocontent:
+ infocontent = infocontent.strip()
+ sections = info.findAll('a', { 'href' : re.compile('^/Sections') })
+ lists = info.findAll('a', { 'href' : re.compile('^/List') })
+ keywords = info.findAll('a', { 'href' : re.compile('^/keyword') })
+ #print 'key=%s content=%r keywords=%r sections=%r lists=%r' % (key, infocontent, keywords, sections, lists)
+ if len(infocontent) > 0:
+ self.info[key] = infocontent
elif len(sections) > 0:
items = []
for item in sections:
- items.append(item.string)
+ items.append(item.contents[0].strip())
self.info[key] = ' / '.join(items)
elif len(lists) > 0:
items = []
for item in lists:
- items.append(item.string)
+ items.append(item.contents[0].strip())
self.info[key] = ' / '.join(items)
+ elif len(keywords) > 0:
+ items = []
+ for item in keywords:
+ items.append(item.contents[0].strip())
+ self.info[key] = ' / '.join(items)
except:
pass
- # Find Plot Outline/Summary:
- # Normally the tag is named "Plot Outline:" - however sometimes
- # the tag is "Plot Summary:" or just "Plot:". Search for all strings.
- imdb_result = soup.find(text='Plot Outline:')
- if not imdb_result:
- imdb_result = soup.find(text='Plot Summary:')
- if not imdb_result:
- imdb_result = soup.find(text='Plot:')
- if imdb_result:
- self.info['plot'] = imdb_result.next.strip()
- else:
- self.info['plot'] = u''
-
- # Find tagline - sometimes the tagline is missing.
- # Use an empty string if no tagline could be found.
- imdb_result = soup.find(text='Tagline:')
- if imdb_result:
- self.info['tagline'] = imdb_result.next.strip()
- else:
- self.info['tagline'] = u''
-
rating = soup.find(text='User Rating:').findNext(text=re.compile('/10'))
- if rating:
+ try:
votes = rating.findNext('a')
- self.info['rating'] = rating.strip() + ' (' + votes.string.strip() + ')'
- else:
+ self.info['rating'] = rating.strip() + ' (' + votes.contents[0].strip() + ')'
+ except AttributeError:
self.info['rating'] = ''
- runtime = soup.find(text='Runtime:')
- if runtime and runtime.next:
- self.info['runtime'] = runtime.next.strip()
- else:
- self.info['runtime'] = ''
-
# Replace special characters in the items
for (k,v) in self.info.items():
self.info[k] = self.convert_entities(v)
@@ -794,10 +799,14 @@
_debug_('parsesearchdata(results=%r, url=%r, id=%r)' % (results, url, id))
self.id_list = []
- m = re.compile('/title/tt([0-9]*)/')
- y = re.compile('\(([^)]+)\)')
+ m = re.compile('/title/tt(\d+)/')
+ y = re.compile('\((\d+)\) *(.*)')
try:
- soup = BeautifulSoup(results.read(), convertEntities='xml')
+ if using_html5lib:
+ parser = HTMLParser(tree=treebuilders.getTreeBuilder('beautifulsoup'))
+ soup = parser.parse(results.read())
+ else:
+ soup = BeautifulSoup(results.read(), convertEntities=BeautifulStoneSoup.HTML_ENTITIES)
except HTMLParser.HTMLParseError, why:
traceback.print_exc()
_debug_('Cannot parse %r: %s' % (url, why), DWARNING)
@@ -806,28 +815,37 @@
traceback.print_exc()
_debug_('Cannot parse %r: %s' % (url, why), DWARNING)
return self.id_list
- items = soup.findAll('a', href=re.compile('/title/tt'))
+ items = soup.findAll('a', href=re.compile('^/title/tt'))
ids = set([])
for item in items:
- idm = m.search(item['href'])
+ idm = item.attrMap['href']
if not idm:
continue
- if isinstance(item.next.next, NavigableString):
- yrm = y.findall(item.next.next)
-
- id = idm.group(1)
- name = item.string
- # skip empty names
- if not name:
+ m_match = m.match(idm)
+ if not m_match:
+ # skip invalid titles
continue
- # skip duplicate ids
+ id = m_match.group(1)
if id in ids:
+ # skip duplicate ids
continue
+ name = item.contents[0]
+ if not isinstance(name, NavigableString):
+ # skip empty names
+ continue
+ if isinstance(item.next.next, NavigableString):
+ yrm = item.next.next.strip()
ids.add(id)
- year = len(yrm) > 0 and yrm[0] or '0000'
- type = len(yrm) > 1 and yrm[1] or ''
+ y_match = y.match(yrm)
+ if y_match:
+ year = y_match.group(1)
+ type = y_match.group(2)
+ else:
+ year = '0000'
+ type = ''
#print 'url', item['href']
#print item.parent.findChildren(text=re.compile('[^ ]'))
+ #print 'id=%s name=%s year=%s type=%s' % (id, name, year, type)
self.id_list += [ ( id, name, year, type ) ]
for item in self.id_list:
@@ -840,7 +858,11 @@
Returns a new id for getIMDBid with TV series episode data
"""
try:
- soup = BeautifulSoup(results.read(), convertEntities='xml')
+ if using_html5lib:
+ parser = HTMLParser(tree=treebuilders.getTreeBuilder('beautifulsoup'))
+ soup = parser.parse(results.read())
+ else:
+ soup = BeautifulSoup(results.read(), convertEntities=BeautifulStoneSoup.HTML_ENTITIES)
except UnicodeDecodeError:
print "Unicode error; check that /usr/lib/python2.x/site.py has the correct default encoding"
pass
@@ -968,9 +990,6 @@
self.image = vfs.basename(self.image)
_debug_('Downloaded cover image from %s' % (self.image_url))
- print "Freevo knows nothing about the copyright of this image, please"
- print "go to %s to check for more information about private." % self.image_url
- print "use of this image"
def str2XML(self, line):
|
