diginaut/digimarks
1
0
Fork 0
mirror of https://github.com/aquatix/digimarks.git synced 2025-12-06 20:55:10 +01:00
Code Issues Releases Wiki Activity

Use a custom User Agent string to prevent server blockage

Browse Source
This commit is contained in:
Michiel Scholten
2018-03-23 10:44:23 +01:00
parent 37ebdda933
commit fefb317ddf
1 changed files with 7 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
digimarks.py
View File

@@ -22,6 +22,8 @@ except ImportError:
from urlparse import urljoin, urlparse, urlunparse from urlparse import urljoin, urlparse, urlunparse
DIGIMARKS_USER_AGENT = 'digimarks/1.2.0-dev'
DEFAULT_THEME = 'green' DEFAULT_THEME = 'green'
themes = { themes = {
'green': { 'green': {
@@ -280,7 +282,7 @@ class Bookmark(BaseModel):
def set_title_from_source(self): def set_title_from_source(self):
""" Request the title by requesting the source url """ """ Request the title by requesting the source url """
try: try:
result = requests.get(self.url) result = requests.get(self.url, headers={'User-Agent': DIGIMARKS_USER_AGENT})
self.http_status = result.status_code self.http_status = result.status_code
except: except:
# For example 'MissingSchema: Invalid URL 'abc': No schema supplied. Perhaps you meant http://abc?' # For example 'MissingSchema: Invalid URL 'abc': No schema supplied. Perhaps you meant http://abc?'
@@ -296,7 +298,7 @@ class Bookmark(BaseModel):
def set_status_code(self): def set_status_code(self):
""" Check the HTTP status of the url, as it might not exist for example """ """ Check the HTTP status of the url, as it might not exist for example """
try: try:
result = requests.head(self.url) result = requests.head(self.url, headers={'User-Agent': DIGIMARKS_USER_AGENT})
self.http_status = result.status_code self.http_status = result.status_code
except requests.ConnectionError: except requests.ConnectionError:
self.http_status = self.HTTP_CONNECTIONERROR self.http_status = self.HTTP_CONNECTIONERROR
@@ -310,10 +312,10 @@ class Bookmark(BaseModel):
# if file exists, don't re-download it # if file exists, don't re-download it
#response = requests.get('http://www.google.com/s2/favicons?domain=' + domain, stream=True) #response = requests.get('http://www.google.com/s2/favicons?domain=' + domain, stream=True)
fileextension = '.png' fileextension = '.png'
meta = requests.head('http://icons.better-idea.org/icon?size=60&url=' + domain, allow_redirects=True) meta = requests.head('http://icons.better-idea.org/icon?size=60&url=' + domain, allow_redirects=True, headers={'User-Agent': DIGIMARKS_USER_AGENT})
if meta.url[-3:].lower() == 'ico': if meta.url[-3:].lower() == 'ico':
fileextension = '.ico' fileextension = '.ico'
response = requests.get('http://icons.better-idea.org/icon?size=60&url=' + domain, stream=True) response = requests.get('http://icons.better-idea.org/icon?size=60&url=' + domain, stream=True, headers={'User-Agent': DIGIMARKS_USER_AGENT})
filename = os.path.join(MEDIA_ROOT, 'favicons/' + domain + fileextension) filename = os.path.join(MEDIA_ROOT, 'favicons/' + domain + fileextension)
with open(filename, 'wb') as out_file: with open(filename, 'wb') as out_file:
shutil.copyfileobj(response.raw, out_file) shutil.copyfileobj(response.raw, out_file)
@@ -339,7 +341,7 @@ class Bookmark(BaseModel):
if self.redirect_uri: if self.redirect_uri:
return self.redirect_uri return self.redirect_uri
if self.http_status == 301 or self.http_status == 302: if self.http_status == 301 or self.http_status == 302:
result = requests.head(self.url, allow_redirects=True) result = requests.head(self.url, allow_redirects=True, headers={'User-Agent': DIGIMARKS_USER_AGENT})
self.http_status = result.status_code self.http_status = result.status_code
self.redirect_uri = result.url self.redirect_uri = result.url
return result.url return result.url