indymedia
/
epicyon
mirror of https://gitlab.com/bashrc2/epicyon
7
4
Fork 1
Code Issues 14 Releases Wiki Activity

Variable name

main
Bob Mottram 2020-11-22 12:41:54 +00:00
parent ea30903c70
commit 22f21ba1f0
1 changed files with 36 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

72
newswire.py
View File

@ -234,38 +234,38 @@ def atomFeedToDict(baseDir: str, domain: str, xmlStr: str,
if '<entry>' not in xmlStr: if '<entry>' not in xmlStr:
return {} return {}
result = {} result = {}
rssItems = xmlStr.split('<entry>') atomItems = xmlStr.split('<entry>')
postCtr = 0 postCtr = 0
maxBytes = maxFeedItemSizeKb * 1024 maxBytes = maxFeedItemSizeKb * 1024
for rssItem in rssItems: for atomItem in atomItems:
if len(rssItem) > maxBytes: if len(atomItem) > maxBytes:
print('WARN: atom feed item is too big') print('WARN: atom feed item is too big')
continue continue
if '<title>' not in rssItem: if '<title>' not in atomItem:
continue continue
if '</title>' not in rssItem: if '</title>' not in atomItem:
continue continue
if '<link>' not in rssItem: if '<link>' not in atomItem:
continue continue
if '</link>' not in rssItem: if '</link>' not in atomItem:
continue continue
if '<updated>' not in rssItem: if '<updated>' not in atomItem:
continue continue
if '</updated>' not in rssItem: if '</updated>' not in atomItem:
continue continue
title = rssItem.split('<title>')[1] title = atomItem.split('<title>')[1]
title = removeCDATA(title.split('</title>')[0]) title = removeCDATA(title.split('</title>')[0])
description = '' description = ''
if '<summary>' in rssItem and '</summary>' in rssItem: if '<summary>' in atomItem and '</summary>' in atomItem:
description = rssItem.split('<summary>')[1] description = atomItem.split('<summary>')[1]
description = removeCDATA(description.split('</summary>')[0]) description = removeCDATA(description.split('</summary>')[0])
else: else:
if '<media:description>' in rssItem and \ if '<media:description>' in atomItem and \
'</media:description>' in rssItem: '</media:description>' in atomItem:
description = rssItem.split('<media:description>')[1] description = atomItem.split('<media:description>')[1]
description = description.split('</media:description>')[0] description = description.split('</media:description>')[0]
description = removeCDATA(description) description = removeCDATA(description)
link = rssItem.split('<link>')[1] link = atomItem.split('<link>')[1]
link = link.split('</link>')[0] link = link.split('</link>')[0]
if '://' not in link: if '://' not in link:
continue continue
@ -274,7 +274,7 @@ def atomFeedToDict(baseDir: str, domain: str, xmlStr: str,
itemDomain = itemDomain.split('/')[0] itemDomain = itemDomain.split('/')[0]
if isBlockedDomain(baseDir, itemDomain): if isBlockedDomain(baseDir, itemDomain):
continue continue
pubDate = rssItem.split('<updated>')[1] pubDate = atomItem.split('<updated>')[1]
pubDate = pubDate.split('</updated>')[0] pubDate = pubDate.split('</updated>')[0]
parsed = False parsed = False
try: try:
@ -325,42 +325,42 @@ def atomFeedYTToDict(baseDir: str, domain: str, xmlStr: str,
if isBlockedDomain(baseDir, 'www.youtube.com'): if isBlockedDomain(baseDir, 'www.youtube.com'):
return {} return {}
result = {} result = {}
rssItems = xmlStr.split('<entry>') atomItems = xmlStr.split('<entry>')
postCtr = 0 postCtr = 0
maxBytes = maxFeedItemSizeKb * 1024 maxBytes = maxFeedItemSizeKb * 1024
for rssItem in rssItems: for atomItem in atomItems:
print('YouTube feed item: ' + rssItem) print('YouTube feed item: ' + atomItem)
if len(rssItem) > maxBytes: if len(atomItem) > maxBytes:
print('WARN: atom feed item is too big') print('WARN: atom feed item is too big')
continue continue
if '<title>' not in rssItem: if '<title>' not in atomItem:
continue continue
if '</title>' not in rssItem: if '</title>' not in atomItem:
continue continue
if '<updated>' not in rssItem: if '<updated>' not in atomItem:
continue continue
if '</updated>' not in rssItem: if '</updated>' not in atomItem:
continue continue
if '<yt:videoId>' not in rssItem: if '<yt:videoId>' not in atomItem:
continue continue
if '</yt:videoId>' not in rssItem: if '</yt:videoId>' not in atomItem:
continue continue
title = rssItem.split('<title>')[1] title = atomItem.split('<title>')[1]
title = removeCDATA(title.split('</title>')[0]) title = removeCDATA(title.split('</title>')[0])
description = '' description = ''
if '<media:description>' in rssItem and \ if '<media:description>' in atomItem and \
'</media:description>' in rssItem: '</media:description>' in atomItem:
description = rssItem.split('<media:description>')[1] description = atomItem.split('<media:description>')[1]
description = description.split('</media:description>')[0] description = description.split('</media:description>')[0]
description = removeCDATA(description) description = removeCDATA(description)
elif '<summary>' in rssItem and '</summary>' in rssItem: elif '<summary>' in atomItem and '</summary>' in atomItem:
description = rssItem.split('<summary>')[1] description = atomItem.split('<summary>')[1]
description = description.split('</summary>')[0] description = description.split('</summary>')[0]
description = removeCDATA(description) description = removeCDATA(description)
link = rssItem.split('<yt:videoId>')[1] link = atomItem.split('<yt:videoId>')[1]
link = link.split('</yt:videoId>')[0] link = link.split('</yt:videoId>')[0]
link = 'https://www.youtube.com/watch?v=' + link.strip() link = 'https://www.youtube.com/watch?v=' + link.strip()
pubDate = rssItem.split('<updated>')[1] pubDate = atomItem.split('<updated>')[1]
pubDate = pubDate.split('</updated>')[0] pubDate = pubDate.split('</updated>')[0]
parsed = False parsed = False
try: try:
@ -417,7 +417,7 @@ def xmlStrToDict(baseDir: str, domain: str, xmlStr: str,
xmlStr, moderated, mirrored, xmlStr, moderated, mirrored,
maxPostsPerSource, maxFeedItemSizeKb) maxPostsPerSource, maxFeedItemSizeKb)
elif '<yt:videoId>' in xmlStr and '<yt:channelId>' in xmlStr: elif '<yt:videoId>' in xmlStr and '<yt:channelId>' in xmlStr:
print ('YouTube feed: reading') print('YouTube feed: reading')
return atomFeedYTToDict(baseDir, domain, return atomFeedYTToDict(baseDir, domain,
xmlStr, moderated, mirrored, xmlStr, moderated, mirrored,
maxPostsPerSource, maxFeedItemSizeKb) maxPostsPerSource, maxFeedItemSizeKb)