Python get_pacer_doc_id_from_doc1_url示例

示例#1

 def test_get_pacer_document_number_from_doc1_url(self):
     qa_pairs = (
         ('https://ecf.almd.uscourts.gov/doc1/01712427473', '01712427473'),
         ('/doc1/01712427473', '01712427473'),
     )
     for q, a in qa_pairs:
         self.assertEqual(get_pacer_doc_id_from_doc1_url(q), a)

示例#2

文件： test_pacer.py 项目： janderse/juriscraper

 def test_get_pacer_document_number_from_doc1_url(self):
     qa_pairs = (
         ('https://ecf.almd.uscourts.gov/doc1/01712427473', '01702427473'),
         ('/doc1/01712427473', '01702427473'),
         ('https://ecf.akb.uscourts.gov/doc1/02201247000?caseid=7738&de_seq_num=723284&dm_id=1204742&doc_num=8805&pdf_header=0', '02201247000'),
     )
     for q, a in qa_pairs:
         self.assertEqual(get_pacer_doc_id_from_doc1_url(q), a)

示例#3

文件： test_pacer.py 项目： umeboshi2/juriscraper

 def test_get_pacer_document_number_from_doc1_url(self):
     qa_pairs = (
         ('https://ecf.almd.uscourts.gov/doc1/01712427473', '01702427473'),
         ('/doc1/01712427473', '01702427473'),
         ('https://ecf.akb.uscourts.gov/doc1/02201247000?caseid=7738&de_seq_num=723284&dm_id=1204742&doc_num=8805&pdf_header=0', '02201247000'),
     )
     for q, a in qa_pairs:
         self.assertEqual(get_pacer_doc_id_from_doc1_url(q), a)

示例#4

文件： attachment_page.py 项目： voutilad/juriscraper

 def _get_pacer_doc_id(row):
     """Take in a row from the attachment table and return the pacer_doc_id
     for the item in that row. Return None if the ID cannot be found.
     """
     try:
         url = row.xpath(u'.//a')[0]
     except IndexError:
         # Item exists, but cannot download document. Perhaps it's sealed
         # or otherwise unavailable in PACER. This is carried over from the
         # docket report and may not be needed here, but it's a good
         # precaution.
         return None
     else:
         doc1_url = url.xpath('./@href')[0]
         return get_pacer_doc_id_from_doc1_url(doc1_url)

示例#5

文件： attachment_page.py 项目： Wright-will/juriscraper

 def _get_pacer_doc_id(row):
     """Take in a row from the attachment table and return the pacer_doc_id
     for the item in that row. Return None if the ID cannot be found.
     """
     try:
         url = row.xpath(u'.//a')[0]
     except IndexError:
         # Item exists, but cannot download document. Perhaps it's sealed
         # or otherwise unavailable in PACER. This is carried over from the
         # docket report and may not be needed here, but it's a good
         # precaution.
         return None
     else:
         doc1_url = url.xpath('./@href')[0]
         return get_pacer_doc_id_from_doc1_url(doc1_url)

示例#6

文件： free_documents.py 项目： cgruppioni/juriscraper

 def get_pacer_doc_id(self):
     doc1_url = self.element.xpath('./td[3]//@href')[0]
     return get_pacer_doc_id_from_doc1_url(doc1_url)