oly
/
hackspace
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Fix pull image from description fallback using string instead of stream

This commit is contained in:
Oly 2018-09-19 13:14:21 +01:00
parent 9d0588e6a1
commit d8c853ee38
1 changed files with 2 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
mhackspace/feeds/reader.py
View File

@ -1,9 +1,7 @@
import lxml import lxml
import feedparser import feedparser
from operator import itemgetter from io import StringIO
from lxml import etree
from lxml.html.clean import Cleaner from lxml.html.clean import Cleaner
from io import StringIO, BytesIO
from django.utils.html import escape from django.utils.html import escape
@ -20,10 +18,6 @@ html_parser = lxml.etree.HTMLParser()
def parse_content(content): def parse_content(content):
headers = {
"User-Agent": "Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0"
}
html_img_cleaner = Cleaner(allow_tags=["img"], remove_unknown_tags=False) html_img_cleaner = Cleaner(allow_tags=["img"], remove_unknown_tags=False)
html_img_cleaner.allow_tags = ["img"] html_img_cleaner.allow_tags = ["img"]
@ -35,9 +29,8 @@ def parse_content(content):
def fetch_image_from_node_text(text): def fetch_image_from_node_text(text):
description = lxml.etree.parse(text, html_parser) description = lxml.etree.parse(StringIO(text), html_parser)
for image in description.xpath(".//img"): for image in description.xpath(".//img"):
print("fetch image from node text")
return image.get("src") return image.get("src")
return None return None
@ -58,14 +51,11 @@ def fetch_node_text(node, name, default=u""):
def fetch_image(post, node, namespaces): def fetch_image(post, node, namespaces):
"""Try and get an image from an item in the feed, use various fall back methods""" """Try and get an image from an item in the feed, use various fall back methods"""
if hasattr(post, "media_thumbnail"): if hasattr(post, "media_thumbnail"):
print("media")
image = post.media_thumbnail image = post.media_thumbnail
print(image)
if image: if image:
return image[0].get("url") return image[0].get("url")
if hasattr(post, "content"): if hasattr(post, "content"):
print("content")
content = " ".join(c.value for c in post.content) content = " ".join(c.value for c in post.content)
image = fetch_image_from_node_text(content) image = fetch_image_from_node_text(content)
if image: if image:
@ -74,7 +64,6 @@ def fetch_image(post, node, namespaces):
# final attempt at getting an image from the item using description # final attempt at getting an image from the item using description
result = fetch_node_text(node, "description") result = fetch_node_text(node, "description")
if result: if result:
print("description")
image = fetch_image_from_node_text(result) image = fetch_image_from_node_text(result)
if image: if image:
return image return image