Created
November 1, 2019 19:29
-
-
Save nbhasker/df5f66e3f0cb9512f1616cebf8fe4e86 to your computer and use it in GitHub Desktop.
Combine Yahoo Groups email messages downloaded via YahooGroupArchiver to HTML (and then to PDF via browser print function)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os | |
import json | |
import datetime | |
import io | |
dir_name = r'C:\Users\Bhasker\Documents\mydocs\src\YahooEmailToHTML\EmailFull' | |
outfile_name = "output.html" | |
start_msg_no = 15000 | |
num_msgs_per_file = 5000 | |
msgs = [] | |
for f_name in os.listdir(dir_name): | |
if f_name.endswith(".json") and "_raw.json" not in f_name: | |
print "Loading ", (os.path.join(dir_name, f_name)) | |
else: | |
continue | |
with open(os.path.join(dir_name, f_name)) as j: | |
d = json.load(j) | |
msgs.append(d) | |
if "attachmentsInfo" in d: | |
for a in d["attachmentsInfo"]: | |
print "Attachment Filename: ", a["filename"] | |
if len(d["authorName"]) == 0: | |
print "Zero length authorName. Using: ", d["from"] | |
print "Found ", len(msgs), " messages" | |
outf = io.open(outfile_name, 'w', encoding='utf8') | |
print "Sorting ..." | |
sorted_msgs = sorted(msgs, key=lambda i: (i["topicId"], i["msgId"])) | |
print "Done" | |
msg_no = 0 | |
msg_count = 0 | |
for m in sorted_msgs: | |
if msg_no < start_msg_no: | |
msg_no += 1 | |
continue; | |
if msg_count >= num_msgs_per_file: | |
break; | |
t = datetime.datetime.utcfromtimestamp(float(m["postDate"])).strftime('%B %#d, %Y %H:%M:%S (UTC)') | |
if len(m["authorName"]) <> 0: | |
s = u"<h1>" + m["authorName"] + u" : " + unicode(t, "utf-8") + u"</h1>" + u"\n" | |
else: | |
s = u"<h1>" + m["from"] + u" : " + unicode(t, "utf-8") + u"</h1>" + u"\n" | |
print "Processing ", m["authorName"], " / ", m["from"] | |
outf.write(s) | |
if "subject" in m: | |
s = u"<h2>" + m["subject"] + u"</h2>" + u"\n" | |
outf.write(s) | |
if "messageBody" in m: | |
outf.write(m["messageBody"]) | |
if "attachmentsInfo" in m and len(m["attachmentsInfo"]) > 0: | |
s = u"<h2>Attachments:</h2>\n" | |
outf.write(s) | |
s = u"\n" + u"<ul>" + u"\n" | |
outf.write(s) | |
for a in m["attachmentsInfo"]: | |
s = u"<li>" + a["filename"] + u"</li>" + u"\n" | |
outf.write(s) | |
s = u"</ul>" + u"\n" | |
outf.write(s) | |
s = u"<hr><br></br>\n" | |
outf.write(s) | |
msg_count += 1 | |
print "Start Msg Number: ", start_msg_no, "Processed Messages: ", msg_count | |
outf.close() | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment