git-sync/crawlab
1
0
Fork 0
mirror of https://github.com/crawlab-team/crawlab.git synced 2026-01-22 17:31:03 +01:00
Code Issues Packages Projects Releases Wiki Activity

fixed bugs

Browse Source
This commit is contained in:
Marvin Zhang
2019-05-29 19:34:51 +08:00
parent 543fe61445
commit 558b7472f8
1 changed files with 7 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
crawlab/routes/spiders.py
View File

@@ -4,6 +4,7 @@ import shutil
import subprocess
from datetime import datetime
from random import random
from urllib.parse import urlparse
import gevent
import requests
@@ -101,7 +102,7 @@ class SpiderApi(BaseApi):
('pagination_selector_type', str),
# whether to obey robots.txt
('obey_robots_txt', str),
('obey_robots_txt', bool),
)
def get(self, id=None, action=None):
@@ -523,7 +524,8 @@ class SpiderApi(BaseApi):
tags = []
for tag in sel.iter():
if tag.tag == 'a':
if tag.get('href') is not None and not tag.get('href').startswith('#') and not tag.get('href').startswith('javascript'):
if tag.get('href') is not None and not tag.get('href').startswith('#') and not tag.get(
'href').startswith('javascript'):
tags.append(tag)
return tags
@@ -566,6 +568,9 @@ class SpiderApi(BaseApi):
if f.get('is_detail'):
url = d.get(f['name'])
if url is not None:
if not url.startswith('http') and not url.startswith('//'):
u = urlparse(spider['start_url'])
url = f'{u.scheme}://{u.netloc}{url}'
ev_list.append(gevent.spawn(get_detail_page_data, url, spider, idx, data))
break
@@ -657,7 +662,6 @@ class SpiderApi(BaseApi):
'query': f'{tag.tag}.{cls_str}',
})
return {
'status': 'ok',
'item_selector': item_selector,