def get_sitting_urls(assembly_id, div_id, sessionurl):
root = get.webpage(get.htmltree(sessionurl))
js_calls = [parse_js_call(j) for j in root.xpath('.//a/@href')]
params = match_name_codes(js_calls, filter='mainsearch2', type='sessions')
nsittings = len(params)
params['j'] = str(nsittings)
urls = []
for i in range(nsittings):
params['SES_NUM'] = params['SES_NUM%s' % i]
url = '%s&%s' % (sessionurl, urlencode(params))
# TODO: generalize me
url = url.replace('con_search2', 'con_search3')
urls.append({'session_name': params['SES_NUM'], 'url': url})
return urls
def get_sitting_urls(assembly_id, div_id, sessionurl):
root = get.webpage(get.htmltree(sessionurl))
js_calls = [parse_js_call(j) for j in root.xpath('.//a/@href')]
params = match_name_codes(js_calls,
filter='mainsearch2',
type='sessions')
nsittings = len(params)
params['j'] = str(nsittings)
urls = []
for i in range(nsittings):
params['SES_NUM'] = params['SES_NUM%s' % i]
url = '%s&%s' % (sessionurl, urlencode(params))
# TODO: generalize me
url = url.replace('con_search2', 'con_search3')
urls.append({'session_name': params['SES_NUM'], 'url': url})
return urls
def get_session_urls(assembly_id, div_id, listurl):
def searchform(root, num=''):
return root.xpath('.//form[@name="searchform%s"]/@action' % num)[0]
root = get.webpage(get.htmltree(listurl))
js_calls = [parse_js_call(j) for j in root.xpath('.//a/@href')]
params = match_name_codes(js_calls, filter='mainsearch', type='committees')
nsessions = len(params)/2
params['i'] = str(nsessions)
params['div'] = str(div_id)
params['DAE_NUM'] = str(assembly_id)
urls = []
for i in range(nsessions):
params['COMM_NAME'] = params['COMM_NAME%s' % i]
params['COMM_CODE'] = params['COMM_CODE%s' % i]
urls.append(\
{'committee': params['COMM_NAME'],
'url': '%s/content/%s?%s' %\
(BASEURL, searchform(root)[:-2], urlencode(params))})
return urls
def get_session_urls(assembly_id, div_id, listurl):
def searchform(root, num=''):
return root.xpath('.//form[@name="searchform%s"]/@action' % num)[0]
root = get.webpage(get.htmltree(listurl))
js_calls = [parse_js_call(j) for j in root.xpath('.//a/@href')]
params = match_name_codes(js_calls, filter='mainsearch', type='committees')
nsessions = len(params) / 2
params['i'] = str(nsessions)
params['div'] = str(div_id)
params['DAE_NUM'] = str(assembly_id)
urls = []
for i in range(nsessions):
params['COMM_NAME'] = params['COMM_NAME%s' % i]
params['COMM_CODE'] = params['COMM_CODE%s' % i]
urls.append(\
{'committee': params['COMM_NAME'],
'url': '%s/content/%s?%s' %\
(BASEURL, searchform(root)[:-2], urlencode(params))})
return urls
def get_doc_ids(assembly_id, div_id, sittingurl):
root = get.webpage(get.htmltree(sittingurl))
js_calls = [parse_js_call(j) for j in root.xpath('.//a/@href')]
return [{'sitting_name': c[1][0], 'docid': c[1][1]}\
for c in js_calls if c[0]=='mainsearch4']
def get_doc_ids(assembly_id, div_id, sittingurl):
root = get.webpage(get.htmltree(sittingurl))
js_calls = [parse_js_call(j) for j in root.xpath('.//a/@href')]
return [{'sitting_name': c[1][0], 'docid': c[1][1]}\
for c in js_calls if c[0]=='mainsearch4']