Используя BS4, как я могу получить указанные c теги только в XML?

Question

в приведенном ниже фрагменте у меня есть две разные записи.

В ЛИНИИ мы видим, что один - это Заработок, а другой - сообщение о приобретении.

<?xml version="1.0" encoding="UTF-8"?>
<Response>
   <Record key="18AD026E657696BE1A7AE7C0D1CE94EF321EFD4C203B31A1F87DD27DEF345872" req_sym="OUT1V-FI">
      <Fields>
         <Field id="7000" name="HEADLINE" value="CORRECTED TRANSCRIPT: Outokumpu Oyj(OUT1V-FI), Q3 2019 Earnings Call, 31-October-2019 9:00 AM ET" />
         <Field id="7001" name="SOURCE" value="FCST" />
         <Field id="7003" name="ALL_IDS" value="OUT1V-FI" />
         <Field id="7046" name="PRIMARY_IDS" value="OUT1V-FI" />
         <Field id="7004" name="STORY_DATE" value="20191101" />
         <Field id="7005" name="STORY_TIME" value="041606" />
         <Field id="7007" name="CATEGORIES" value="CN:FI,DT:EARN,DT:ERNS,DT:ER_GEN,DT:EVTS,DT:EV_ME,DT:FILNS_TS_TR,IN:METAL,LN:EN,RN:EU,RN:NE,SB:ERNS,SB:ER_GEN,SB:EVTS,SB:EV_ME" />
         <Field id="7002" name="SEARCH_IDS" value="OUT1V-FI" />
         <Field id="7011" name="LINK1" value="https://datadirect.factset.com/services/docretrieval?report=feed&amp;key=U2FsdGVkX1%2fEHwXn0zpAkqjR%2bJOkauoxw0LQ2BhLtraPMDZwyAwoN9WuYQ8PMM4ZKNAXx8VpWFsDe2T%2fZ7WNdQ%3d%3d&amp;timezone=America/New_York" />
         <Field id="7039" name="FILING_SIZE" value="NULL" />
         <Field id="8000" name="EVENT_IDS" value="1201149455" />
         <Field id="8001" name="REPORT_IDS" value="2314010" />
         <Field id="8002" name="EVENTDATE-REPORTID-TRANSCRIPTTYPE" value="20191031-2314010-C" />
         <Field id="8003" name="EVENT" value="E" />
         <Field id="8004" name="UPLOAD_DATE_TIME" value="2019-11-01 22:36:48" />
         <Field id="8005" name="VERSION_ID" value="4379596" />
      </Fields>
   <Record key="0BB357A317B871E3ED0FD0ECBD210D771E8331097964E1D9223C9BEE844E68F2" req_sym="SUBC-NO">
      <Fields>
         <Field id="7000" name="HEADLINE" value="CORRECTED TRANSCRIPT: Subsea 7 SA(SUBC-NO), Acquisition of McDermott International,Inc by Subsea 7 S.A Call, 23-April-2018 9:00 AM ET" />
         <Field id="7001" name="SOURCE" value="FCST" />
         <Field id="7003" name="ALL_IDS" value="SUBC-NO" />
         <Field id="7046" name="PRIMARY_IDS" value="SUBC-NO" />
         <Field id="7004" name="STORY_DATE" value="20180423" />
         <Field id="7005" name="STORY_TIME" value="142404" />
         <Field id="7007" name="CATEGORIES" value="CN:GB,DT:CA_MNA_GEN,DT:CORPS,DT:FILNS_TS_TR,DT:MANDA,IN:OIL,LN:EN,RN:EU,SB:EVTS,SB:MANDA" />
         <Field id="7002" name="SEARCH_IDS" value="SUBC-NO" />
         <Field id="7011" name="LINK1" value="https://datadirect.factset.com/services/docretrieval?report=feed&amp;key=U2FsdGVkX1%2bJsxYfwGoI5ggt7BF%2bBr8ttuTeQZmMIWBDSxPjFIksm%2bjEDqkK5hq4NDxszCncdCgA18qo3qN5SQ%3d%3d&amp;timezone=America/New_York" />
         <Field id="7039" name="FILING_SIZE" value="NULL" />
         <Field id="8000" name="EVENT_IDS" value="6235691" />
         <Field id="8001" name="REPORT_IDS" value="2081721" />
         <Field id="8002" name="EVENTDATE-REPORTID-TRANSCRIPTTYPE" value="20180423-2081721-C" />
         <Field id="8003" name="EVENT" value="SS" />
         <Field id="8004" name="UPLOAD_DATE_TIME" value="2018-04-26 22:35:20" />
         <Field id="8005" name="VERSION_ID" value="3453250" />
      </Fields>
   </Record>
</Response>

Right теперь мой код не может различить две записи.

from bs4 import BeautifulSoup
import pandas as pd
import xml.etree.ElementTree as ET
import glob
import os

path = "/Users/User/Downloads/Thesis papers/links/"
for filename in glob.glob(os.path.join(path, "*")):
    with open(filename) as open_file:
        content = open_file.read()

    bs = BeautifulSoup(content, "xml")
    for individual_xml in bs.find_all("Response"):
        for link in individual_xml.find_all("Fields"):
            for fields in link.find_all("Field", {"id":"7000"}):
                print(fields[])

Как я могу указать, что я хочу, чтобы записи содержались только в том случае, если включены слова "Заработок", как первая запись во фрагменте xml?

Answer 1

Теперь, когда у вас есть ответ, я дам вам другое решение только для справки.

from simplified_scrapy import SimplifiedDoc,req,utils
html = ''' '''
doc = SimplifiedDoc(html)
field = doc.getElementByReg('Earnings Call',tag='Field') # Locate by value
print (field)
field = doc.select('Field#7000') # Get the first Field in the document with id = 7000
# field = doc.select('Response>Fields>Field#7000')
print (field)

Результат:

{'id': '7000', 'name': 'HEADLINE', 'value': 'CORRECTED TRANSCRIPT: Outokumpu Oyj(OUT1V-FI), Q3 2019 Earnings Call, 31-October-2019 9:00 AM ET', 'tag': 'Field'}
{'id': '7000', 'name': 'HEADLINE', 'value': 'CORRECTED TRANSCRIPT: Outokumpu Oyj(OUT1V-FI), Q3 2019 Earnings Call, 31-October-2019 9:00 AM ET', 'tag': 'Field'}

Answer 2

Решил сам.

Вот решение. Просто добавил эти строки в конец:

word = "Earnings Call"
if word in fields["value"]:
    print(fields)