forked from sushant354/judis-re
/
supremecourt.py
289 lines (230 loc) · 9.82 KB
/
supremecourt.py
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
import os
import re
import string
import tempfile
import urllib
import utils
class SupremeCourt(utils.BaseCourt):
def __init__(self, name, rawdir, metadir, statsdir, updateMeta = False):
utils.BaseCourt.__init__(self, name, rawdir, metadir, statsdir, updateMeta)
self.cookiefile = tempfile.NamedTemporaryFile()
self.hostname = 'judis.nic.in'
self.webformUrl = 'http://judis.nic.in/supremecourt/Chrseq.aspx'
self.dateqryUrl = 'http://judis.nic.in/supremecourt/DateQry.aspx'
self.dataTypes = ['A']
self.statevalNames = ['__VIEWSTATE']
def date_postdata(self, dateobj, dataType):
if dateobj.month < 10:
mnth = '0%d' % dateobj.month
else:
mnth = '%d' % dateobj.month
if dateobj.day < 10:
day = '0%d' % dateobj.day
else:
day = '%d' % dateobj.day
postdata = self.state_data()
postdata.extend(
[ ('ddlday1', day), ('ddlmonth1', mnth),\
('ddlyear1', dateobj.year), ('ddlday2', day), \
('ddlmonth2', mnth),('ddlyear2', dateobj.year),\
('ddlreport', dataType), ('button', 'Submit')\
])
return postdata
def download_oneday(self, relpath, dateobj):
newdls = []
for dataType in self.dataTypes:
self.stateval = self.get_stateval(self.dateqryUrl)
if not self.stateval:
self.logger.error(u'No stateval for date %s' % dateobj)
postdata = self.date_postdata(dateobj, dataType)
webpage = self.download_webpage(postdata, self.dateqryUrl)
newdls.extend(self.datequery_result(webpage, relpath, 1, dateobj))
return newdls
def extract_links(self, prsdobj, pagenum):
linkdict = {'docs': []}
trs = prsdobj.findAll('tr')
for tr in trs:
pageblock, nextlink = utils.check_next_page(tr, pagenum)
if nextlink:
linkdict['next'] = nextlink
elif not pageblock:
link = self.get_judgment_info(tr)
if link:
linkdict['docs'].append(link)
return linkdict
def save_meta_tags(self, metapath, judgedict, dateobj):
tagdict = {}
if judgedict.has_key('title'):
title = judgedict['title']
tagdict['title'] = title
reobj = re.search('( vs | vs\.)', title, re.IGNORECASE)
if reobj:
if reobj.start() > 1:
petitioner = title[:reobj.start()]
tagdict['petitioner'] = petitioner
if reobj.end() + 1 < len(title):
respondent = title[reobj.end() + 1:]
tagdict['respondent'] = respondent
if judgedict.has_key('bench'):
bench = judgedict['bench'].split(',')
if len(bench) > 0:
benchdict = {}
benchdict['name'] = []
for judge in bench:
benchdict['name'].append(judge)
tagdict['bench'] = benchdict
tagdict['date'] = utils.date_to_xml(dateobj)
utils.print_tag_file(metapath, tagdict)
def get_judgment_info(self, tr):
judgedict = {}
link = tr.find('a')
if link:
title = utils.get_tag_contents(link)
href = link.get('href')
if title:
judgedict['title'] = title
if href:
judgedict['href'] = href
tds = tr.findAll('td')
for td in tds:
txt = utils.get_tag_contents(td)
reobj = re.search('Coram\s*:', txt)
if reobj and reobj.end() + 1 < len(txt):
bench = txt[reobj.end() + 1:]
judgedict['bench'] = bench
return judgedict
def datequery_result(self, webpage, relpath, pagenum, dateobj):
downloaded = []
d = utils.parse_webpage(webpage)
if not d:
self.logger.error(u'Could not parse html of the result page for date %s' % dateobj)
return downloaded
stateval = self.extract_state(d)
if stateval != None and stateval != self.stateval:
self.stateval = stateval
self.logger.info(u'stateval changed')
linkdict = self.extract_links(d, pagenum)
for link in linkdict['docs']:
if (not link.has_key('title')) or (not link.has_key('href')):
continue
self.logger.info(u'Processing link: %s href: %s' % \
(link['title'], link['href']))
filename = re.sub('/', '|', link['title'])
filename = re.sub("'", ' ', filename)
tmprel = os.path.join (relpath, filename)
rawpath = os.path.join (self.rawdir, tmprel)
metapath = os.path.join (self.metadir, tmprel)
if not os.path.exists(rawpath):
webpage = self.download_judgment(link)
if webpage:
utils.save_file(rawpath, webpage)
else:
self.logger.warning(u'Could not download %s' % \
link['title'])
if os.path.exists(rawpath) and not os.path.isdir(rawpath):
if not os.path.exists(metapath) or self.updateMeta:
self.save_meta_tags(metapath, link, dateobj)
downloaded.append(tmprel)
if linkdict.has_key('next'):
link = linkdict['next']
self.logger.info(u'Following page: %s href: %s' % \
(link['title'], link['href']))
webpage = self.download_link(link)
if webpage:
nextdownloads = self.datequery_result(webpage, relpath, \
pagenum + 1, dateobj)
downloaded.extend(nextdownloads)
else:
self.logger.warning(u'Could not download %s' % link['title'])
return downloaded
def extract_state(self, prsdobj):
stateval = {}
inputs = prsdobj.findAll('input')
for input in inputs:
name = input.get('name')
if name in self.statevalNames:
stateval[name] = input.get('value')
return stateval
def state_data(self):
t = []
for name in self.statevalNames:
if self.stateval.has_key(name):
t.append((name, self.stateval[name]))
return t
def get_stateval(self, url):
webpage = self.download_url(url, \
savecookies = self.cookiefile.name)
d = utils.parse_webpage(webpage)
if d:
return self.extract_state(d)
else:
self.logger.error(u'Could not parse the date webpage')
return None
def download_webpage(self, postdata, posturl):
webpage = self.download_url(posturl, postdata = postdata, \
loadcookies = self.cookiefile.name)
return webpage
def parse_link(self, linkname):
linkRe = "javascript:__doPostBack\('(?P<event_target>[^']+)','(?P<event_arg>[^']*)'\)"
return re.search(linkRe, linkname)
def download_judgment(self, link):
return self.download_link(link)
def download_link(self, link):
linkinfo = self.parse_link(link['href'])
if linkinfo == None:
self.logger.warning(u'Values not in %s. title is %s' % \
(link['href'], link['title']))
return None
eventTarget =string.join(linkinfo.group('event_target').split('$'), ':')
postdata = self.state_data()
postdata.extend([('__EVENTTARGET', eventTarget), \
('__EVENTARGUMENT', linkinfo.group('event_arg'))])
return self.download_webpage(postdata, self.webformUrl)
class NewSC(SupremeCourt):
def __init__(self, name, rawdir, metadir, statsdir, updateMeta = False):
SupremeCourt.__init__(self, name, rawdir, metadir, statsdir, updateMeta)
def download_judgment(self, link):
return self.download_url(link['href'])
def get_judgment_info(self, tr):
links = tr.findAll('a')
judgedict = {}
for link in links:
href = link.get('href')
if href and re.search('imgst.aspx', href):
judgedict['href'] = urllib.basejoin(self.webformUrl, href)
tds = tr.findAll('td')
maxTxt = ''
for td in tds:
txt = utils.get_tag_contents(td)
if not txt:
continue
txt = txt.strip()
reobj = re.search('Coram\s*:', txt)
if reobj and reobj.end() + 1 < len(txt):
bench = txt[reobj.end() + 1:]
judgedict['bench'] = bench
else:
reobj = re.search(' vs\.? ', txt, re.IGNORECASE)
if reobj:
judgedict['title'] = txt
judgedict['petitioner'] = txt[:reobj.start()]
judgedict['respondent'] = txt[reobj.end():]
elif len(maxTxt) < len(txt):
maxTxt = txt
if not judgedict.has_key('title') and maxTxt:
judgedict['title'] = maxTxt
return judgedict
def extract_links(self, prsdobj, pagenum):
linkdict = {'docs': []}
trs = prsdobj.findAll('tr')
for tr in trs:
if tr.find('tr'):
continue
pageblock, nextlink = utils.check_next_page(tr, pagenum)
if nextlink:
linkdict['next'] = nextlink
elif not pageblock:
link = self.get_judgment_info(tr)
if link:
linkdict['docs'].append(link)
return linkdict