nickname 잘못가져오는 버그 수정

git-svn-id: svn://192.168.0.12/source@251 8346c931-da38-4b9b-9d4c-e48b93cbd075
This commit is contained in:
admin
2016-02-01 10:23:32 +00:00
parent eeee7d4565
commit 519e40c9b8

View File

@@ -58,8 +58,9 @@ class FacebookInit(CrawlInit):
# return trimmed_list
def make_url(self):
# return [self.urls[self.platform()] + x + "?fref=ts" for x in self.split_searches()]
return [self.urls[self.platform()] + x for x in self.split_searches()]
return [self.urls[self.platform()] + 'profile.php?id=' + x if x.isnumeric() else x + "?fref=ts"
for x in self.split_searches()]
# return [self.urls[self.platform()] + x for x in self.split_searches()]
# urls = list()
# for x in self.split_searches():
# url = self.urls[self.platform()] + x + "?fref=ts"
@@ -113,11 +114,15 @@ class FacebookBodyCrawler:
def find_article_nickname(self, soup):
nickname = soup.find('div', class_='fbPhotoContributorName')
if not nickname or not nickname.get_text():
span = soup.find('span', class_='fwb fcg')
if span:
nickname = span.a
else:
nickname = soup.find('a', 'profileLink')
temp_nickname = soup.select_one('span.fwb > a')
if temp_nickname.has_attr('href') and temp_nickname.get('href').find(self.find_article_id(soup)) != -1:
nickname = temp_nickname
if not nickname:
span = soup.find('span', class_='fwb fcg')
if span:
nickname = span.a
if not nickname:
nickname = soup.find('a', 'profileLink')
if not nickname:
nickname = soup.find('a', class_='_2yug')
return nickname.get_text() if nickname else ""