tanpengsccd/AV_Data_Capture
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

0.3.2 Beta 完善错误提示

Browse Source
This commit is contained in:
wenead99 2019-05-29 12:10:16 +08:00 committed by GitHub
parent 5f627d24e0
commit b5f82f77a1
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
core.py
View File

@ -12,13 +12,11 @@ import time
#=====================爬虫核心部分========================== #=====================爬虫核心部分==========================
def get_html(url):#网页请求核心 def get_html(url):#网页请求核心
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'} headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'}
getweb = requests.get(str(url),proxies={"http": "http://127.0.0.1:2334","https": "https://127.0.0.1:2334"},timeout=5,headers=headers).text getweb = requests.get(str(url),timeout=5,headers=headers).text
try: try:
return getweb return getweb
except Exception as e: except:
print(e) print("[-]Connect Failed! Please check your Proxy.")
except IOError as e1:
print(e1)
def getTitle(htmlcode): #获取标题 def getTitle(htmlcode): #获取标题
doc = pq(htmlcode) doc = pq(htmlcode)