Skip to content

N
network-assets-reptile
Commit b6fa9839 authored by liyang's avatar liyang
Browse files
Options

fix:爬取数据入库

parent a335d50a
Hide whitespace changes
Inline Side-by-side
Showing with 10 additions and 10 deletions
pc_ptt.py
View file @ b6fa9839
...@@ -120,16 +120,16 @@ def reptile(browser=None, search_word=""): ...@@ -120,16 +120,16 @@ def reptile(browser=None, search_word=""):
log.debug('开始判断类型') log.debug('开始判断类型')
# ---------------- 判断类型 start ---------- # ---------------- 判断类型 start ----------
# 类型 # 类型
content_type = "" content_type = "文字"
try: # try:
# 查找所有img标签 # # 查找所有img标签
img_tags = soup.find_all('img') # img_tags = soup.find_all('img')
if len(img_tags) > 0: # if len(img_tags) > 0:
content_type = "图文" # content_type = "图文"
else: # else:
content_type = "文字" # content_type = "文字"
except: # except:
content_type = "文字" # content_type = "文字"
# ---------------- 判断类型 end ---------- # ---------------- 判断类型 end ----------
log.debug('开始内容过滤') log.debug('开始内容过滤')
# ------------------ content 过滤 start-------------- # ------------------ content 过滤 start--------------
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment