Commit 5d9b5cc8 authored by liyang's avatar liyang

fix:爬取数据入库

parent b6fa9839
......@@ -120,16 +120,16 @@ def reptile(browser=None, search_word=""):
log.debug('开始判断类型')
# ---------------- 判断类型 start ----------
# 类型
content_type = ""
try:
# 查找所有img标签
img_tags = soup.find_all('img')
if len(img_tags) > 0:
content_type = "图文"
else:
content_type = "文字"
except:
content_type = "文字"
# try:
# # 查找所有img标签
# img_tags = soup.find_all('img')
# if len(img_tags) > 0:
# content_type = "图文"
# else:
# content_type = "文字"
# except:
# content_type = "文字"
# ---------------- 判断类型 end ----------
log.debug('开始内容过滤')
# ------------------ content 过滤 start--------------
......@@ -173,15 +173,17 @@ def reptile(browser=None, search_word=""):
}
# --------------- 组装数据 end---------------------
if search_word is "":
data.append(obj)
else:
# 使用正则表达式进行匹配
# matches = re.findall(search_word, element_title.text)
matches = re.findall(search_word, element_title.text)
# 打印匹配结果
# if matches:
# # log.debug(f"找到了匹配的字符串:{matches}")
# data.append(obj)
# else:
# log.debug("未找到匹配的字符串")
if matches:
# log.debug(f"找到了匹配的字符串:{matches}")
data.append(obj)
else:
log.debug("未找到匹配的字符串")
# 浏览器返回上一页
browser.back()
......
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