python3.6安装bs4.6总是出错_init_.py。 10
Traceback(mostrecentcalllast):File"text.py",line3,in<module>frombs4importBeautifulSou...
Traceback (most recent call last):
File "text.py", line 3, in <module>
from bs4 import BeautifulSoup
File "D:\MyDownloads\Download\beautifulsoup4-4.6.0\bs4\__init__.py", line 53
'You are trying to run the Python 2 version of Beautiful Soup under Python 3. This will not work.'<>'You need to convert the code, either by installing it (`python setup.py install`) or by running 2to3 (`2to3 -w bs4`).'
^
SyntaxError: invalid syntax 展开
File "text.py", line 3, in <module>
from bs4 import BeautifulSoup
File "D:\MyDownloads\Download\beautifulsoup4-4.6.0\bs4\__init__.py", line 53
'You are trying to run the Python 2 version of Beautiful Soup under Python 3. This will not work.'<>'You need to convert the code, either by installing it (`python setup.py install`) or by running 2to3 (`2to3 -w bs4`).'
^
SyntaxError: invalid syntax 展开
展开全部
建议卸载之后重装
首先,下载最新版的BeautifulSoup。
下载文件解压。
进入下载目录允许
比如:C:\Download\beautifulsoup4-4.5.1
pythonsetup.py install
但是在进行如下操作的时候
from bs4 import BeautifulSoup
会出现如下错误:
File "C:\Python35\lib\bs4\__init__.py", line 48
'You are trying to run the Python 2 version of Beautiful Soup under python 3. This will not work.'<>'You need to convert the code, either by installing it (`python setup.py install`) or by running 2to3 (`2to3 -w bs4`).'
由于我们是使用最新的版本3.5.2,因此需要把版本python 2 库升级(转换)到3系列的库
python C:\>pythonC:\Users\fuzr1\AppData\Local\Programs\Python\Python35-32\Tools\scripts\2to3.py c:\Download\beautifulsoup4-4.5.1\bs4\
最后出现如下界面:
RefactoringTool: Files that need to be modified:
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\__init__.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\dammit.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\diagnose.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\element.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\testing.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\builder\__init__.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\builder\_html5lib.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\builder\_htmlparser.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\builder\_lxml.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\tests\__init__.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\tests\test_builder_registr
y.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\tests\test_docs.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\tests\test_html5lib.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\tests\test_htmlparser.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\tests\test_lxml.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\tests\test_soup.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\tests\test_tree.py
说明转换已经完成,
验证如下的实例:
python 网络爬虫入门(一)———第一个python爬虫实例
import requests
import csv
import random
import time
import socket
import http.client
#import urllib.request
from bs4 import BeautifulSoup
一切ok。
附带上测试程序:
# -*- coding: gbk -*-
import requests
import csv
import random
import time
import socket
import http.client
# import urllib.request
from bs4 import BeautifulSoup
"""requests:用来抓取网页的html源代码
csv:将数据写入到csv文件中
random:取随机数
time:时间相关操作
socket和http.client 在这里只用于异常处理
BeautifulSoup:用来代替正则式取源码中相应标签中的内容
urllib.request:另一种抓取网页的html源代码的方法,但是没requests方便(我一开始用的是这一种)
获取网页中的html代码:"""
def get_content(url , data = None):
header={
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate, sdch',
'Accept-Language': 'zh-CN,zh;q=0.8',
'Connection': 'keep-alive',
'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.235'
}
timeout = random.choice(range(80, 180))
while True:
try:
rep = requests.get(url,headers = header,timeout = timeout)
rep.encoding = 'utf-8'
# req = urllib.request.Request(url, data, header)
# response = urllib.request.urlopen(req, timeout=timeout)
# html1 = response.read().decode('UTF-8', errors='ignore')
# response.close()
break
# except urllib.request.HTTPError as e:
# print( '1:', e)
# time.sleep(random.choice(range(5, 10)))
#
# except urllib.request.URLError as e:
# print( '2:', e)
# time.sleep(random.choice(range(5, 10)))
except socket.timeout as e:
print( '3:', e)
time.sleep(random.choice(range(8,15)))
except socket.error as e:
print( '4:', e)
time.sleep(random.choice(range(20, 60)))
except http.client.BadStatusLine as e:
print( '5:', e)
time.sleep(random.choice(range(30, 80)))
except http.client.IncompleteRead as e:
print( '6:', e)
time.sleep(random.choice(range(5, 15)))
return rep.text
# return html_text
"""header是requests.get的一个参数,目的是模拟浏览器访问
header 可以使用chrome的开发者工具获得,具体方法如下:
打开chrome,按F12,选择network
重新访问该网站,找到第一个网络请求,查看它的header
timeout是设定的一个超时时间,取随机数是因为防止被网站认定为网络爬虫。
然后通过requests.get方法获取网页的源代码、
rep.encoding = ‘utf-8’是将源代码的编码格式改为utf-8(不该源代码中中文部分会为乱码)
下面是一些异常处理
返回 rep.text
获取html中我们所需要的字段:
这里我们主要要用到BeautifulSoup
首先还是用开发者工具查看网页源码,并找到所需字段的相应位置
找到我们需要字段都在 id = “7d”的“div”的ul中。日期在每个li中h1 中,天气状况在每个li的第一个p标签内,最高温度和最低温度在每个li的span和i标签中。
感谢Joey_Ko指出的错误:到了傍晚,当天气温会没有最高温度,所以要多加一个判断。
代码如下:"""
def get_data(html_text):
final = []
bs = BeautifulSoup(html_text, "html.parser") # 创建BeautifulSoup对象
body = bs.body # 获取body部分
data = body.find('div', {'id': '7d'}) # 找到id为7d的div
ul = data.find('ul') # 获取ul部分
li = ul.find_all('li') # 获取所有的li
for day in li: # 对每个li标签中的内容进行遍历
temp = []
date = day.find('h1').string # 找到日期
temp.append(date) # 添加到temp中
inf = day.find_all('p') # 找到li中的所有p标签
temp.append(inf[0].string,) # 第一个p标签中的内容(天气状况)加到temp中
if inf[1].find('span') is None:
temperature_highest = None # 天气预报可能没有当天的最高气温(到了傍晚,就是这样),需要加个判断语句,来输出最低气温
else:
temperature_highest = inf[1].find('span').string # 找到最高温
temperature_highest = temperature_highest.replace('℃', '') # 到了晚上网站会变,最高温度后面也有个℃
temperature_lowest = inf[1].find('i').string # 找到最低温
temperature_lowest = temperature_lowest.replace('℃', '') # 最低温度后面有个℃,去掉这个符号
temp.append(temperature_highest) # 将最高温添加到temp中
temp.append(temperature_lowest) #将最低温添加到temp中
final.append(temp) #将temp加到final中
return final
"""写入文件csv:
将数据抓取出来后我们要将他们写入文件,具体代码如下:"""
def write_data(data, name):
file_name = name
with open(file_name, 'a', errors='ignore', newline='') as f:
f_csv = csv.writer(f)
f_csv.writerows(data)
#主函数:
if __name__ == '__main__':
url ='
html = get_content(url)
result = get_data(html)
write_data(result, 'weather.csv')
// 把以上代码保存为 get_weather.py
最后运行
python get_weather.py
首先,下载最新版的BeautifulSoup。
下载文件解压。
进入下载目录允许
比如:C:\Download\beautifulsoup4-4.5.1
pythonsetup.py install
但是在进行如下操作的时候
from bs4 import BeautifulSoup
会出现如下错误:
File "C:\Python35\lib\bs4\__init__.py", line 48
'You are trying to run the Python 2 version of Beautiful Soup under python 3. This will not work.'<>'You need to convert the code, either by installing it (`python setup.py install`) or by running 2to3 (`2to3 -w bs4`).'
由于我们是使用最新的版本3.5.2,因此需要把版本python 2 库升级(转换)到3系列的库
python C:\>pythonC:\Users\fuzr1\AppData\Local\Programs\Python\Python35-32\Tools\scripts\2to3.py c:\Download\beautifulsoup4-4.5.1\bs4\
最后出现如下界面:
RefactoringTool: Files that need to be modified:
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\__init__.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\dammit.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\diagnose.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\element.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\testing.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\builder\__init__.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\builder\_html5lib.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\builder\_htmlparser.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\builder\_lxml.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\tests\__init__.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\tests\test_builder_registr
y.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\tests\test_docs.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\tests\test_html5lib.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\tests\test_htmlparser.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\tests\test_lxml.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\tests\test_soup.py
RefactoringTool: c:\Download\beautifulsoup4-4.5.1\bs4\tests\test_tree.py
说明转换已经完成,
验证如下的实例:
python 网络爬虫入门(一)———第一个python爬虫实例
import requests
import csv
import random
import time
import socket
import http.client
#import urllib.request
from bs4 import BeautifulSoup
一切ok。
附带上测试程序:
# -*- coding: gbk -*-
import requests
import csv
import random
import time
import socket
import http.client
# import urllib.request
from bs4 import BeautifulSoup
"""requests:用来抓取网页的html源代码
csv:将数据写入到csv文件中
random:取随机数
time:时间相关操作
socket和http.client 在这里只用于异常处理
BeautifulSoup:用来代替正则式取源码中相应标签中的内容
urllib.request:另一种抓取网页的html源代码的方法,但是没requests方便(我一开始用的是这一种)
获取网页中的html代码:"""
def get_content(url , data = None):
header={
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate, sdch',
'Accept-Language': 'zh-CN,zh;q=0.8',
'Connection': 'keep-alive',
'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.235'
}
timeout = random.choice(range(80, 180))
while True:
try:
rep = requests.get(url,headers = header,timeout = timeout)
rep.encoding = 'utf-8'
# req = urllib.request.Request(url, data, header)
# response = urllib.request.urlopen(req, timeout=timeout)
# html1 = response.read().decode('UTF-8', errors='ignore')
# response.close()
break
# except urllib.request.HTTPError as e:
# print( '1:', e)
# time.sleep(random.choice(range(5, 10)))
#
# except urllib.request.URLError as e:
# print( '2:', e)
# time.sleep(random.choice(range(5, 10)))
except socket.timeout as e:
print( '3:', e)
time.sleep(random.choice(range(8,15)))
except socket.error as e:
print( '4:', e)
time.sleep(random.choice(range(20, 60)))
except http.client.BadStatusLine as e:
print( '5:', e)
time.sleep(random.choice(range(30, 80)))
except http.client.IncompleteRead as e:
print( '6:', e)
time.sleep(random.choice(range(5, 15)))
return rep.text
# return html_text
"""header是requests.get的一个参数,目的是模拟浏览器访问
header 可以使用chrome的开发者工具获得,具体方法如下:
打开chrome,按F12,选择network
重新访问该网站,找到第一个网络请求,查看它的header
timeout是设定的一个超时时间,取随机数是因为防止被网站认定为网络爬虫。
然后通过requests.get方法获取网页的源代码、
rep.encoding = ‘utf-8’是将源代码的编码格式改为utf-8(不该源代码中中文部分会为乱码)
下面是一些异常处理
返回 rep.text
获取html中我们所需要的字段:
这里我们主要要用到BeautifulSoup
首先还是用开发者工具查看网页源码,并找到所需字段的相应位置
找到我们需要字段都在 id = “7d”的“div”的ul中。日期在每个li中h1 中,天气状况在每个li的第一个p标签内,最高温度和最低温度在每个li的span和i标签中。
感谢Joey_Ko指出的错误:到了傍晚,当天气温会没有最高温度,所以要多加一个判断。
代码如下:"""
def get_data(html_text):
final = []
bs = BeautifulSoup(html_text, "html.parser") # 创建BeautifulSoup对象
body = bs.body # 获取body部分
data = body.find('div', {'id': '7d'}) # 找到id为7d的div
ul = data.find('ul') # 获取ul部分
li = ul.find_all('li') # 获取所有的li
for day in li: # 对每个li标签中的内容进行遍历
temp = []
date = day.find('h1').string # 找到日期
temp.append(date) # 添加到temp中
inf = day.find_all('p') # 找到li中的所有p标签
temp.append(inf[0].string,) # 第一个p标签中的内容(天气状况)加到temp中
if inf[1].find('span') is None:
temperature_highest = None # 天气预报可能没有当天的最高气温(到了傍晚,就是这样),需要加个判断语句,来输出最低气温
else:
temperature_highest = inf[1].find('span').string # 找到最高温
temperature_highest = temperature_highest.replace('℃', '') # 到了晚上网站会变,最高温度后面也有个℃
temperature_lowest = inf[1].find('i').string # 找到最低温
temperature_lowest = temperature_lowest.replace('℃', '') # 最低温度后面有个℃,去掉这个符号
temp.append(temperature_highest) # 将最高温添加到temp中
temp.append(temperature_lowest) #将最低温添加到temp中
final.append(temp) #将temp加到final中
return final
"""写入文件csv:
将数据抓取出来后我们要将他们写入文件,具体代码如下:"""
def write_data(data, name):
file_name = name
with open(file_name, 'a', errors='ignore', newline='') as f:
f_csv = csv.writer(f)
f_csv.writerows(data)
#主函数:
if __name__ == '__main__':
url ='
html = get_content(url)
result = get_data(html)
write_data(result, 'weather.csv')
// 把以上代码保存为 get_weather.py
最后运行
python get_weather.py
已赞过
已踩过<
评论
收起
你对这个回答的评价是?
推荐律师服务:
若未解决您的问题,请您详细描述您的问题,通过百度律临进行免费专业咨询