v4l3n71n/web_scrap
1
0
Fork 0
Code Issues Pull Requests Projects Releases 10 Wiki Activity

check image exist in media

Browse Source
This commit is contained in:
Valentin CZERYBA 2023-03-30 23:50:25 +02:00
parent 301f1e2d4b
commit c92f24e6af
1 changed files with 33 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
insert_wordpress.py
View File

@ -48,12 +48,20 @@ class WPimport:
href_a = i.get("href")
href_img = img[0].get("src")
page_img = requests.get(href_img)
img_break = False
if page_img.status_code == 404:
href_img = href_a
img_break = True
page = requests.get(href_img)
if page.status_code == 200:
split_fileimg = href_img.split("/")
img_name = split_fileimg[len(split_fileimg)-1]
params = { "search": img_name}
r = requests.get("http://{0}/wp-json/wp/v2/media".format(self.wordpress), auth=self.basic, params=params)
if r.status_code == 200:
res = r.json()
if len(res) == 0:
data = page.content
img_type = "image/png"
if img_name.split(".")[1]:
@ -61,12 +69,16 @@ class WPimport:
headers={ 'Content-Type': img_type,'Content-Disposition' : 'attachment; filename={0}'.format(img_name)}
r = requests.post("http://{0}/wp-json/wp/v2/media".format(self.wordpress), auth=self.basic, headers=headers, data=data)
if r.status_code == 201:
res = r.json()
new_img["old_src"]=href_img
new_img["id"]=r.json()["id"]
new_img["new_src"]=r.json()["guid"]["rendered"]
new_img["old_href"]=href_a
new_img["id"]=res["id"]
new_img["new_src"]=res["guid"]["rendered"]
new_img["break"]=img_break
list_img.append(new_img)
print(list_img)
exit(0)
comment_post = []
for i in comment:
comment_item = i.text.split("\n")
@ -112,6 +124,16 @@ class WPimport:
else:
bodyhtml = bodyhtml + str(i).replace("<p>", "").replace("</p>", "").replace("<br>", "<br />") + "<br />"
bodyhtml = bodyhtml + "</p>"
for i in list_img:
o = urlparse(i["new_src"])
if i == True:
print(i["old_href"])
bodyhtml = bodyhtml.replace(i["old_href"], o.path)
else:
print(i["old_src"])
bodyhtml = bodyhtml.replace(i["old_src"], o.path)
print(bodyhtml)
exit(0)
hour = articledate[0].text
time = dateheader[0].text.split(" ")