从文档中提取文本

您可能会发现,仅从文档中提取文本很有用。如果您要将文本传递给其他 API 服务,这会很有用。文档中的所有文本都包含在段落元素文本运行中。文本可出现在文档的 3 种结构元素中:

  • 段落
  • 目录

表可以嵌套在另一个表中。因此,如需提取文档中的所有文本,您必须访问每个嵌套结构元素。

有关文档正文的完整说明,请参阅文档结构指南。

以下示例使用递归来访问文档中的每个结构元素并输出文本。

Java

// Copyright 2019 Google LLC
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
//     http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.

import com.google.api.client.auth.oauth2.Credential;
import com.google.api.client.extensions.java6.auth.oauth2.AuthorizationCodeInstalledApp;
import com.google.api.client.extensions.jetty.auth.oauth2.LocalServerReceiver;
import com.google.api.client.googleapis.auth.oauth2.GoogleAuthorizationCodeFlow;
import com.google.api.client.googleapis.auth.oauth2.GoogleClientSecrets;
import com.google.api.client.googleapis.javanet.GoogleNetHttpTransport;
import com.google.api.client.http.javanet.NetHttpTransport;
import com.google.api.client.json.JsonFactory;
import com.google.api.client.json.jackson2.JacksonFactory;
import com.google.api.client.util.store.FileDataStoreFactory;
import com.google.api.services.docs.v1.Docs;
import com.google.api.services.docs.v1.DocsScopes;
import com.google.api.services.docs.v1.model.Document;
import com.google.api.services.docs.v1.model.ParagraphElement;
import com.google.api.services.docs.v1.model.StructuralElement;
import com.google.api.services.docs.v1.model.TableCell;
import com.google.api.services.docs.v1.model.TableRow;
import com.google.api.services.docs.v1.model.TextRun;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.security.GeneralSecurityException;
import java.util.Collections;
import java.util.List;

public class ExtractText {
  private static final String APPLICATION_NAME = "Google Docs API Extract Guide";
  private static final JsonFactory JSON_FACTORY = JacksonFactory.getDefaultInstance();
  private static final String TOKENS_DIRECTORY_PATH = "tokens";
  private static final String DOCUMENT_ID = "YOUR_DOCUMENT_ID";

  /**
   * Global instance of the scopes required by this quickstart. If modifying these scopes, delete
   * your previously saved tokens/ folder.
   */
  private static final List<String> SCOPES =
      Collections.singletonList(DocsScopes.DOCUMENTS_READONLY);

  private static final String CREDENTIALS_FILE_PATH = "/credentials.json";

  /**
   * Creates an authorized Credential object.
   *
   * @param HTTP_TRANSPORT The network HTTP Transport.
   * @return An authorized Credential object.
   * @throws IOException If the credentials.json file cannot be found.
   */
  private static Credential getCredentials(final NetHttpTransport HTTP_TRANSPORT)
      throws IOException {
    // Load client secrets.
    InputStream in = ExtractText.class.getResourceAsStream(CREDENTIALS_FILE_PATH);
    GoogleClientSecrets clientSecrets =
        GoogleClientSecrets.load(JSON_FACTORY, new InputStreamReader(in));

    // Build flow and trigger user authorization request.
    GoogleAuthorizationCodeFlow flow =
        new GoogleAuthorizationCodeFlow.Builder(HTTP_TRANSPORT, JSON_FACTORY, clientSecrets, SCOPES)
            .setDataStoreFactory(new FileDataStoreFactory(new java.io.File(TOKENS_DIRECTORY_PATH)))
            .setAccessType("offline")
            .build();
    LocalServerReceiver receiver = new LocalServerReceiver.Builder().setPort(8888).build();
    return new AuthorizationCodeInstalledApp(flow, receiver).authorize("user");
  }

  /**
   * Returns the text in the given ParagraphElement.
   *
   * @param element a ParagraphElement from a Google Doc
   */
  private static String readParagraphElement(ParagraphElement element) {
    TextRun run = element.getTextRun();
    if (run == null || run.getContent() == null) {
      // The TextRun can be null if there is an inline object.
      return "";
    }
    return run.getContent();
  }

  /**
   * Recurses through a list of Structural Elements to read a document's text where text may be in
   * nested elements.
   *
   * @param elements a list of Structural Elements
   */
  private static String readStructuralElements(List<StructuralElement> elements) {
    StringBuilder sb = new StringBuilder();
    for (StructuralElement element : elements) {
      if (element.getParagraph() != null) {
        for (ParagraphElement paragraphElement : element.getParagraph().getElements()) {
          sb.append(readParagraphElement(paragraphElement));
        }
      } else if (element.getTable() != null) {
        // The text in table cells are in nested Structural Elements and tables may be
        // nested.
        for (TableRow row : element.getTable().getTableRows()) {
          for (TableCell cell : row.getTableCells()) {
            sb.append(readStructuralElements(cell.getContent()));
          }
        }
      } else if (element.getTableOfContents() != null) {
        // The text in the TOC is also in a Structural Element.
        sb.append(readStructuralElements(element.getTableOfContents().getContent()));
      }
    }
    return sb.toString();
  }

  public static void main(String... args) throws IOException, GeneralSecurityException {
    // Build a new authorized API client service.
    final NetHttpTransport HTTP_TRANSPORT = GoogleNetHttpTransport.newTrustedTransport();
    Docs service =
        new Docs.Builder(HTTP_TRANSPORT, JSON_FACTORY, getCredentials(HTTP_TRANSPORT))
            .setApplicationName(APPLICATION_NAME)
            .build();

    Document doc = service.documents().get(DOCUMENT_ID).execute();
    System.out.println(readStructuralElements(doc.getBody().getContent()));
  }
}

Python

# Copyright 2019 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""
Recursively extracts the text from a Google Doc.
"""
import googleapiclient.discovery as discovery
from httplib2 import Http
from oauth2client import client
from oauth2client import file
from oauth2client import tools

SCOPES = 'https://www.googleapis.com/auth/documents.readonly'
DISCOVERY_DOC = 'https://docs.googleapis.com/$discovery/rest?version=v1'
DOCUMENT_ID = 'YOUR_DOCUMENT_ID'


def get_credentials():
    """Gets valid user credentials from storage.

    If nothing has been stored, or if the stored credentials are invalid,
    the OAuth 2.0 flow is completed to obtain the new credentials.

    Returns:
        Credentials, the obtained credential.
    """
    store = file.Storage('token.json')
    credentials = store.get()

    if not credentials or credentials.invalid:
        flow = client.flow_from_clientsecrets('credentials.json', SCOPES)
        credentials = tools.run_flow(flow, store)
    return credentials

def read_paragraph_element(element):
    """Returns the text in the given ParagraphElement.

        Args:
            element: a ParagraphElement from a Google Doc.
    """
    text_run = element.get('textRun')
    if not text_run:
        return ''
    return text_run.get('content')


def read_structural_elements(elements):
    """Recurses through a list of Structural Elements to read a document's text where text may be
        in nested elements.

        Args:
            elements: a list of Structural Elements.
    """
    text = ''
    for value in elements:
        if 'paragraph' in value:
            elements = value.get('paragraph').get('elements')
            for elem in elements:
                text += read_paragraph_element(elem)
        elif 'table' in value:
            # The text in table cells are in nested Structural Elements and tables may be
            # nested.
            table = value.get('table')
            for row in table.get('tableRows'):
                cells = row.get('tableCells')
                for cell in cells:
                    text += read_structural_elements(cell.get('content'))
        elif 'tableOfContents' in value:
            # The text in the TOC is also in a Structural Element.
            toc = value.get('tableOfContents')
            text += read_structural_elements(toc.get('content'))
    return text


def main():
    """Uses the Docs API to print out the text of a document."""
    credentials = get_credentials()
    http = credentials.authorize(Http())
    docs_service = discovery.build(
        'docs', 'v1', http=http, discoveryServiceUrl=DISCOVERY_DOC)
    doc = docs_service.documents().get(documentId=DOCUMENT_ID).execute()
    doc_content = doc.get('body').get('content')
    print(read_structural_elements(doc_content))

if __name__ == '__main__':
    main()