一、网上摘录的https://blog.csdn.net/xunkhun/article/details/79349621
def getHTMLText(url):
try:
r = requests.get(url)
r.raise_for_status()
r.encoding = r.apparent_encoding
return r.text
except:
return "产生异常"
r.raise_for_status()会跑出异常,没有异常则是None。抓取一切异常
二、自己用的,也是抄袭这位博文(https://blog.csdn.net/polyhedronx/article/details/81589196)
def get_text_from_url(url):
# 从链接中获取网页文本
try:
response = requests.get(url, headers=headers, timeout=30)
if response.status_code == 200:
return response.text
else:
print('get page failed.', response.status_code)
return None
except (ConnectionError, TimeoutError) as e:
print('crawling failed', url, e)
return None