Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

change li to div and connection #19

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

change li to div and connection #19

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3af0903
fix parser and connection
Oct 7, 2018
0c84eba
refine
Oct 7, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 4 additions & 5 deletions xgoogle/browser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,12 +81,11 @@ def __init__(self, user_agent=BROWSERS[0], debug=False, use_pool=False):
self.debug = debug

def get_page(self, url, data=None):
handlers = [PoolHTTPHandler]
opener = urllib2.build_opener(*handlers)
if data: data = urllib.urlencode(data)
request = urllib2.Request(url, data, self.headers)
opener = urllib2.build_opener()
opener.addheaders = [('User-agent', 'Mozilla/5.0')]

try:
response = opener.open(request)
response = opener.open(url)
return response.read()
except (urllib2.HTTPError, urllib2.URLError), e:
raise BrowserError(url, str(e))
Expand Down
6 changes: 3 additions & 3 deletions xgoogle/search.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -205,7 +205,6 @@ def _get_results_page(self):
page = self.browser.get_page(safe_url)
except BrowserError, e:
raise SearchError, "Failed getting %s: %s" % (e.url, e.error)

return BeautifulSoup(page)

def _extract_info(self, soup):
Expand All @@ -226,7 +225,7 @@ def _extract_info(self, soup):
return {'from': int(matches.group(1)), 'to': int(matches.group(2)), 'total': int(matches.group(3))}

def _extract_results(self, soup):
results = soup.findAll('li', {'class': 'g'})
results = soup.findAll('div', {'class': 'g'})
ret_res = []
for result in results:
eres = self._extract_result(result)
Expand All @@ -237,7 +236,8 @@ def _extract_results(self, soup):
def _extract_result(self, result):
title, url = self._extract_title_url(result)
desc = self._extract_description(result)
if not title or not url or not desc:
desc = desc is None and desc or ""
if not title or not url :
return None
return SearchResult(title, url, desc)

Expand Down