Python : 将标签 (gmail) 中的所有电子邮件下载为 pdf
Python : download as pdf all emails from a label (gmail)
我想以 pdf 格式从 gmail 下载 100 多封电子邮件。通过 gmail 中的打印选项手动下载所有这些文件太长了。
此 python 脚本检索所选标签中的电子邮件。如何将此电子邮件转换为 pdf。
# source = https://developers.google.com/gmail/api/quickstart/python?authuser=2
from __future__ import print_function
import pickle
import os.path
from googleapiclient.discovery import build
from google_auth_oauthlib.flow import InstalledAppFlow
from google.auth.transport.requests import Request
SCOPES = ['https://www.googleapis.com/auth/gmail.readonly']
def main():
creds = None
if os.path.exists('token.pickle'):
with open('token.pickle', 'rb') as token:
creds = pickle.load(token)
# If there are no (valid) credentials available, let the user log in.
if not creds or not creds.valid:
if creds and creds.expired and creds.refresh_token:
creds.refresh(Request())
else:
flow = InstalledAppFlow.from_client_secrets_file(
'credentials.json', SCOPES)
creds = flow.run_local_server()
# Save the credentials for the next run
with open('token.pickle', 'wb') as token:
pickle.dump(creds, token)
service = build('gmail', 'v1', credentials=creds)
# Call the Gmail API
response= service.users().messages().list(userId="me", labelIds="Label_53", q=None, pageToken=None, maxResults=None, includeSpamTrash=None).execute()
all_message_in_label = []
if 'messages' in response:
all_message_in_label.extend(response['messages'])
while 'nextPageToken' in response:
page_token = response['nextPageToken']
response = service.users().messages().list(userId="me", labelIds="Label_53", q=None, pageToken=page_token, maxResults=None, includeSpamTrash=None).execute()
all_message_in_label.extend(response['messages'])
if not all_message_in_label:
print('No email LM found.')
else:
# get message from Id listed in all_message_in_label
for emails in all_message_in_label:
message= service.users().messages().get(userId="me", id=emails["id"], format="raw", metadataHeaders=None).execute()
if __name__ == '__main__':
main()
我对你的问题做了一些挖掘，发现了一些可能有用的 link：
关于将您的消息转换为 .eml 格式 link.
从 .eml 转换为 .pdf 这些 links:
eml2pdf 是一个 python github 项目，它将 eml 文件转换为 pdf，但我不确定它是否有效。你可以检查一下，看看它是否有效。
eml-to-pdf 是另一个 github 项目，它看起来很差但仍然有效。它写在 javascript.
还有 pyPdf 可以用来生成 pdf 文件。尽管这样您可能需要自己转换电子邮件并设置格式。
有关消息对象格式的更多信息，您可以参考 gmail api python 文档 get 方法。
here 是一个博客 post，它使用不同的方法来满足您的需求，但我不确定它是否仍然有效.
希望对您有所帮助。祝你好运。
我尝试了 Ali Nuri Seker 回答中的建议，但没有用：
- eml2pdf：无法在 Windows
上工作
- eml-to-pdf：Mime 类型错误
- pyPdf：构建整个设计需要做的工作太多
- gmail-to-pdf：某些电子邮件的代码错误（参见 github 中提到的错误）
什么有效（与 Ali Nuri Seker 相同的总体思路）：
- 使用
email.generator.Generator 将电子邮件保存为 .eml
- 使用 eml-to-pdf-converter（不是基于 python，而是开源 GUI）将 .eml 文件转换为 pdf（您基本上只需删除包含 .eml 文件的文件夹，单击按钮，然后你就得到了你的 pdf。它甚至可以与子文件夹一起使用！）
可以找到更详细的脚本here
这是第一个脚本"save email as .eml":
# source = https://developers.google.com/gmail/api/quickstart/python?authuser=2
# In brief:
# this script will connect to your gmail account and download as .eml file your email from a specified label.
# then you can convert the .eml files to pdf : https://github.com/nickrussler/eml-to-pdf-converter
# set up
# 1) save this script in a folder
# 2) save the script "get labels id.py" in the same folder
# 3) go to this link https://developers.google.com/gmail/api/quickstart/python and click on "Enable the gmail API", then click on "Download client configuration" and save this .json file in the same folder as this script
# 4) GMAIL API doesn't use Label name but ID so you need to run the script "get labels id.py" and to copy the ID for the label you need (the firt time, you will be ask the persmission on a consent screen, accept it with the account where you want to download your email)
# 5) copy your label id below in custom var
# 6) run this script and your emails will be saved as .eml file in a subfolder "emails as eml"
# connect to gmail api
from __future__ import print_function
import pickle
import os.path
from googleapiclient.discovery import build
from google_auth_oauthlib.flow import InstalledAppFlow
from google.auth.transport.requests import Request
# decode response from Gmail api and save a email
import base64
import email
#for working dir and path for saving file
import os
# CUSTOM VAR
labelid = "Label_18" # change your label id
# set working directory
abspath = os.path.abspath(__file__)
dname = os.path.dirname(abspath)
os.chdir(dname)
print("working dir set to ", dname)
# create folder to save email
emailfolder= dname+"\emails as eml"
if not os.path.exists(emailfolder):
os.makedirs(emailfolder)
# If modifying these scopes, delete the file token.pickle.
SCOPES = ['https://www.googleapis.com/auth/gmail.readonly']
def main():
# create the credential the first tim and save then in token.pickle
creds = None
if os.path.exists('token.pickle'):
with open('token.pickle', 'rb') as token:
creds = pickle.load(token)
if not creds or not creds.valid:
if creds and creds.expired and creds.refresh_token:
creds.refresh(Request())
else:
flow = InstalledAppFlow.from_client_secrets_file(
'credentials.json', SCOPES)
creds = flow.run_local_server()
with open('token.pickle', 'wb') as token:
pickle.dump(creds, token)
#create the service
service = build('gmail', 'v1', credentials=creds)
# get the *list* of all emails in the labels (if there are multiple pages, navigate to them)
#*************************************
# ressources for *list* email by labels
# https://developers.google.com/resources/api-libraries/documentation/gmail/v1/python/latest/index.html
# https://developers.google.com/resources/api-libraries/documentation/gmail/v1/python/latest/gmail_v1.users.messages.html#list
# example of code for list: https://developers.google.com/gmail/api/v1/reference/users/messages/list?apix_params=%7B%22userId%22%3A%22me%22%2C%22includeSpamTrash%22%3Afalse%2C%22labelIds%22%3A%5B%22LM%22%5D%7D
#*************************************
response= service.users().messages().list(userId="me", labelIds=labelid, q=None, pageToken=None, maxResults=None, includeSpamTrash=None).execute()
all_message_in_label = []
if 'messages' in response:
all_message_in_label.extend(response['messages'])
while 'nextPageToken' in response:
page_token = response['nextPageToken']
response = service.users().messages().list(userId="me", labelIds=labelid, q=None, pageToken=page_token, maxResults=None, includeSpamTrash=None).execute()
all_message_in_label.extend(response['messages'])
# all_message_in_label looks like this
# for email in all_message_in_label:
# print(email)
#{'id': '169735e289ba7310', 'threadId': '169735e289ba7310'}
#{'id': '169735c76a4b93af', 'threadId': '169735c76a4b93af'}
if not all_message_in_label:
print('No email LM found.')
else:
# for each ID in all_message_in_label we *get* the message
#*************************************
# ressources for *get* email
# https://developers.google.com/resources/api-libraries/documentation/gmail/v1/python/latest/gmail_v1.users.messages.html#get
# code example for decode https://developers.google.com/gmail/api/v1/reference/users/messages/get
# + decode for python 3 https://python-forum.io/Thread-TypeError-initial-value-must-be-str-or-None-not-bytes--12161
#*************************************
for emails in all_message_in_label:
message= service.users().messages().get(userId="me", id=emails["id"], format="raw", metadataHeaders=None).execute()
msg_str = base64.urlsafe_b64decode(message['raw'].encode('ASCII'))
try:
mime_msg = email.message_from_string(msg_str.decode())
# the the message as a .eml file
outfile_name = os.path.join(emailfolder, f'{emails["id"]}.eml')
with open(outfile_name, 'w') as outfile:
gen = email.generator.Generator(outfile)
gen.flatten(mime_msg)
print("mail saved: ", emails["id"])
except:
print("error in message ", message["snippet"])
if __name__ == '__main__':
main()
这是第二个脚本 "get labels ids.py"（参见第一个脚本中的 "Set up" 第 4 步）
# source = https://developers.google.com/gmail/api/quickstart/python?authuser=2
from __future__ import print_function
import pickle
import os.path
from googleapiclient.discovery import build
from google_auth_oauthlib.flow import InstalledAppFlow
from google.auth.transport.requests import Request
# If modifying these scopes, delete the file token.pickle.
SCOPES = ['https://www.googleapis.com/auth/gmail.readonly']
def main():
creds = None
if os.path.exists('token.pickle'):
with open('token.pickle', 'rb') as token:
creds = pickle.load(token)
if not creds or not creds.valid:
if creds and creds.expired and creds.refresh_token:
creds.refresh(Request())
else:
flow = InstalledAppFlow.from_client_secrets_file(
'credentials.json', SCOPES)
creds = flow.run_local_server()
with open('token.pickle', 'wb') as token:
pickle.dump(creds, token)
service = build('gmail', 'v1', credentials=creds)
# Get list of all labels
# https://developers.google.com/resources/api-libraries/documentation/gmail/v1/python/latest/index.html
results = service.users().labels().list(userId='me').execute()
labels = results.get('labels', [])
if not labels:
print('No labels found.')
else:
print('Labels:')
for label in labels:
print(label['name'] + " "+label['id'])
if __name__ == '__main__':
main()
input("continue")
我想以 pdf 格式从 gmail 下载 100 多封电子邮件。通过 gmail 中的打印选项手动下载所有这些文件太长了。
此 python 脚本检索所选标签中的电子邮件。如何将此电子邮件转换为 pdf。
# source = https://developers.google.com/gmail/api/quickstart/python?authuser=2
from __future__ import print_function
import pickle
import os.path
from googleapiclient.discovery import build
from google_auth_oauthlib.flow import InstalledAppFlow
from google.auth.transport.requests import Request
SCOPES = ['https://www.googleapis.com/auth/gmail.readonly']
def main():
creds = None
if os.path.exists('token.pickle'):
with open('token.pickle', 'rb') as token:
creds = pickle.load(token)
# If there are no (valid) credentials available, let the user log in.
if not creds or not creds.valid:
if creds and creds.expired and creds.refresh_token:
creds.refresh(Request())
else:
flow = InstalledAppFlow.from_client_secrets_file(
'credentials.json', SCOPES)
creds = flow.run_local_server()
# Save the credentials for the next run
with open('token.pickle', 'wb') as token:
pickle.dump(creds, token)
service = build('gmail', 'v1', credentials=creds)
# Call the Gmail API
response= service.users().messages().list(userId="me", labelIds="Label_53", q=None, pageToken=None, maxResults=None, includeSpamTrash=None).execute()
all_message_in_label = []
if 'messages' in response:
all_message_in_label.extend(response['messages'])
while 'nextPageToken' in response:
page_token = response['nextPageToken']
response = service.users().messages().list(userId="me", labelIds="Label_53", q=None, pageToken=page_token, maxResults=None, includeSpamTrash=None).execute()
all_message_in_label.extend(response['messages'])
if not all_message_in_label:
print('No email LM found.')
else:
# get message from Id listed in all_message_in_label
for emails in all_message_in_label:
message= service.users().messages().get(userId="me", id=emails["id"], format="raw", metadataHeaders=None).execute()
if __name__ == '__main__':
main()
我对你的问题做了一些挖掘，发现了一些可能有用的 link：
关于将您的消息转换为 .eml 格式
从 .eml 转换为 .pdf 这些 links:
eml2pdf 是一个 python github 项目，它将 eml 文件转换为 pdf，但我不确定它是否有效。你可以检查一下，看看它是否有效。
eml-to-pdf 是另一个 github 项目，它看起来很差但仍然有效。它写在 javascript.
还有 pyPdf 可以用来生成 pdf 文件。尽管这样您可能需要自己转换电子邮件并设置格式。
有关消息对象格式的更多信息，您可以参考 gmail api python 文档 get 方法。
here 是一个博客 post，它使用不同的方法来满足您的需求，但我不确定它是否仍然有效.
希望对您有所帮助。祝你好运。
我尝试了 Ali Nuri Seker 回答中的建议，但没有用：
- eml2pdf：无法在 Windows
上工作
- eml-to-pdf：Mime 类型错误
- pyPdf：构建整个设计需要做的工作太多
- gmail-to-pdf：某些电子邮件的代码错误（参见 github 中提到的错误）
什么有效（与 Ali Nuri Seker 相同的总体思路）：
- 使用
email.generator.Generator 将电子邮件保存为 .eml
- 使用 eml-to-pdf-converter（不是基于 python，而是开源 GUI）将 .eml 文件转换为 pdf（您基本上只需删除包含 .eml 文件的文件夹，单击按钮，然后你就得到了你的 pdf。它甚至可以与子文件夹一起使用！）
可以找到更详细的脚本here
这是第一个脚本"save email as .eml":
# source = https://developers.google.com/gmail/api/quickstart/python?authuser=2
# In brief:
# this script will connect to your gmail account and download as .eml file your email from a specified label.
# then you can convert the .eml files to pdf : https://github.com/nickrussler/eml-to-pdf-converter
# set up
# 1) save this script in a folder
# 2) save the script "get labels id.py" in the same folder
# 3) go to this link https://developers.google.com/gmail/api/quickstart/python and click on "Enable the gmail API", then click on "Download client configuration" and save this .json file in the same folder as this script
# 4) GMAIL API doesn't use Label name but ID so you need to run the script "get labels id.py" and to copy the ID for the label you need (the firt time, you will be ask the persmission on a consent screen, accept it with the account where you want to download your email)
# 5) copy your label id below in custom var
# 6) run this script and your emails will be saved as .eml file in a subfolder "emails as eml"
# connect to gmail api
from __future__ import print_function
import pickle
import os.path
from googleapiclient.discovery import build
from google_auth_oauthlib.flow import InstalledAppFlow
from google.auth.transport.requests import Request
# decode response from Gmail api and save a email
import base64
import email
#for working dir and path for saving file
import os
# CUSTOM VAR
labelid = "Label_18" # change your label id
# set working directory
abspath = os.path.abspath(__file__)
dname = os.path.dirname(abspath)
os.chdir(dname)
print("working dir set to ", dname)
# create folder to save email
emailfolder= dname+"\emails as eml"
if not os.path.exists(emailfolder):
os.makedirs(emailfolder)
# If modifying these scopes, delete the file token.pickle.
SCOPES = ['https://www.googleapis.com/auth/gmail.readonly']
def main():
# create the credential the first tim and save then in token.pickle
creds = None
if os.path.exists('token.pickle'):
with open('token.pickle', 'rb') as token:
creds = pickle.load(token)
if not creds or not creds.valid:
if creds and creds.expired and creds.refresh_token:
creds.refresh(Request())
else:
flow = InstalledAppFlow.from_client_secrets_file(
'credentials.json', SCOPES)
creds = flow.run_local_server()
with open('token.pickle', 'wb') as token:
pickle.dump(creds, token)
#create the service
service = build('gmail', 'v1', credentials=creds)
# get the *list* of all emails in the labels (if there are multiple pages, navigate to them)
#*************************************
# ressources for *list* email by labels
# https://developers.google.com/resources/api-libraries/documentation/gmail/v1/python/latest/index.html
# https://developers.google.com/resources/api-libraries/documentation/gmail/v1/python/latest/gmail_v1.users.messages.html#list
# example of code for list: https://developers.google.com/gmail/api/v1/reference/users/messages/list?apix_params=%7B%22userId%22%3A%22me%22%2C%22includeSpamTrash%22%3Afalse%2C%22labelIds%22%3A%5B%22LM%22%5D%7D
#*************************************
response= service.users().messages().list(userId="me", labelIds=labelid, q=None, pageToken=None, maxResults=None, includeSpamTrash=None).execute()
all_message_in_label = []
if 'messages' in response:
all_message_in_label.extend(response['messages'])
while 'nextPageToken' in response:
page_token = response['nextPageToken']
response = service.users().messages().list(userId="me", labelIds=labelid, q=None, pageToken=page_token, maxResults=None, includeSpamTrash=None).execute()
all_message_in_label.extend(response['messages'])
# all_message_in_label looks like this
# for email in all_message_in_label:
# print(email)
#{'id': '169735e289ba7310', 'threadId': '169735e289ba7310'}
#{'id': '169735c76a4b93af', 'threadId': '169735c76a4b93af'}
if not all_message_in_label:
print('No email LM found.')
else:
# for each ID in all_message_in_label we *get* the message
#*************************************
# ressources for *get* email
# https://developers.google.com/resources/api-libraries/documentation/gmail/v1/python/latest/gmail_v1.users.messages.html#get
# code example for decode https://developers.google.com/gmail/api/v1/reference/users/messages/get
# + decode for python 3 https://python-forum.io/Thread-TypeError-initial-value-must-be-str-or-None-not-bytes--12161
#*************************************
for emails in all_message_in_label:
message= service.users().messages().get(userId="me", id=emails["id"], format="raw", metadataHeaders=None).execute()
msg_str = base64.urlsafe_b64decode(message['raw'].encode('ASCII'))
try:
mime_msg = email.message_from_string(msg_str.decode())
# the the message as a .eml file
outfile_name = os.path.join(emailfolder, f'{emails["id"]}.eml')
with open(outfile_name, 'w') as outfile:
gen = email.generator.Generator(outfile)
gen.flatten(mime_msg)
print("mail saved: ", emails["id"])
except:
print("error in message ", message["snippet"])
if __name__ == '__main__':
main()
这是第二个脚本 "get labels ids.py"（参见第一个脚本中的 "Set up" 第 4 步）
# source = https://developers.google.com/gmail/api/quickstart/python?authuser=2
from __future__ import print_function
import pickle
import os.path
from googleapiclient.discovery import build
from google_auth_oauthlib.flow import InstalledAppFlow
from google.auth.transport.requests import Request
# If modifying these scopes, delete the file token.pickle.
SCOPES = ['https://www.googleapis.com/auth/gmail.readonly']
def main():
creds = None
if os.path.exists('token.pickle'):
with open('token.pickle', 'rb') as token:
creds = pickle.load(token)
if not creds or not creds.valid:
if creds and creds.expired and creds.refresh_token:
creds.refresh(Request())
else:
flow = InstalledAppFlow.from_client_secrets_file(
'credentials.json', SCOPES)
creds = flow.run_local_server()
with open('token.pickle', 'wb') as token:
pickle.dump(creds, token)
service = build('gmail', 'v1', credentials=creds)
# Get list of all labels
# https://developers.google.com/resources/api-libraries/documentation/gmail/v1/python/latest/index.html
results = service.users().labels().list(userId='me').execute()
labels = results.get('labels', [])
if not labels:
print('No labels found.')
else:
print('Labels:')
for label in labels:
print(label['name'] + " "+label['id'])
if __name__ == '__main__':
main()
input("continue")