去掉转义字符
我回来了~{:10_256:}问题也来拜访我了{:10_245:}
请问这里的转义字符如何去掉?
import requests
from bs4 import BeautifulSoup
try:
#爬虫模块
response = requests.get("http://www.weather.com.cn/weather1d/101230301.shtml")
response.encoding = "utf-8"
#网页内容提取模块
bs = BeautifulSoup(response.text,'html.parser')
# print(bs.find_all('div',class_='t'))
content1 = bs.find_all('p',class_='tem');content1_=[]
content2 = bs.find_all('p',class_='wea');content2_=[]
content3 = bs.find_all('p',class_='win');content3_=[]
content4 = bs.find_all('p',class_='sun sunUp');content4_=[]
content5 = bs.find_all('p',class_='sun sunDown');content5_=[]
content6 = bs.find_all('ul',class_='clearfix');content6_=[]
content6 = ]
#打印
for content in content1:
content1_.append(content.get_text())
for content in content2:
content2_.append(content.get_text())
for content in content3:
content3_.append(content.get_text())
for content in content4:
content4_.append(content.get_text())
for content in content5:
content5_.append(content.get_text())
for content in content6:
content6_.append(content.get_text())
print(content1_)
print(content2_)
print(content3_)
print(content4_)
print(content5_)
print(content6_)
except Exception as e:
#打印异常信息
print(e)
输出:
['\n24°C\n', '\n31°C\n']
['中雨', '小雨']
['\n\n<3级\n', '<3级']
['\n日出 05:16\n']
['\n日落 18:40\n']
['\n\n12日夜间\n\n中雨\n\n\n\n24°C\n\n\n\n<3级\n\n\n日落 18:40\n\n\n\n\n13日白天\n\n小雨\n\n天空阴沉\n\n\n天预报综合天气现象、能见度、空气质量等因子,预测未来一周的天空状况。\n\n\n天空蔚蓝\n可见透彻蓝天,或有蓝天白云美景\n\n\n天空淡蓝\n天空不够清澈,以浅蓝色为主\n\n\n天空阴沉\n阴天或有雨雪,天空灰暗\n\n\n天空灰霾\n出现霾或沙尘,天空灰蒙浑浊\n\n\n\n\n\n\n31°C\n\n<3级\n\n日出 05:16\n\n\n']
import requests
from bs4 import BeautifulSoup
try:
#爬虫模块
response = requests.get("http://www.weather.com.cn/weather1d/101230301.shtml")
response.encoding = "utf-8"
#网页内容提取模块
bs = BeautifulSoup(response.text,'html.parser')
# print(bs.find_all('div',class_='t'))
content1 = bs.find_all('p',class_='tem');content1_=[]
content2 = bs.find_all('p',class_='wea');content2_=[]
content3 = bs.find_all('p',class_='win');content3_=[]
content4 = bs.find_all('p',class_='sun sunUp');content4_=[]
content5 = bs.find_all('p',class_='sun sunDown');content5_=[]
content6 = bs.find_all('ul',class_='clearfix');content6_=[]
content6 = ]
#打印
for index in range(1,7):
for content in eval(f'content{index}'):
print(content.get_text())
except Exception as e:
#打印异常信息
print(e)
import requests
from bs4 import BeautifulSoup
try:
#爬虫模块
response = requests.get("http://www.weather.com.cn/weather1d/101230301.shtml")
response.encoding = "utf-8"
#网页内容提取模块
bs = BeautifulSoup(response.text,'html.parser')
# print(bs.find_all('div',class_='t'))
content1 = bs.find_all('p',class_='tem');content1_=[]
content2 = bs.find_all('p',class_='wea');content2_=[]
content3 = bs.find_all('p',class_='win');content3_=[]
content4 = bs.find_all('p',class_='sun sunUp');content4_=[]
content5 = bs.find_all('p',class_='sun sunDown');content5_=[]
content6 = bs.find_all('ul',class_='clearfix');content6_=[]
content6 = ]
#打印
for index in range(1,7):
for content in eval(f'content{index}'):
eval(f'content{index}_').append(content.get_text().replace('\n',''))
print(eval(f'content{index}_'))
except Exception as e:
#打印异常信息
print(e)
简单点用replace替换就可以了
页:
[1]