python 55讲的课后作业,Python交流,编程语言专区,鱼C论坛

fresh_python 发表于 2020-3-28 19:11:36

python 55讲的课后作业

请教各位大神，发现小甲鱼几年前写的代码爬取百度百科时会出错。我应该怎么改呢？
import urllib.request
import urllib.parse
import re
from bs4 import BeautifulSoup

def test_url(soup):
result = soup.find(text=re.compile("百度百科尚未收录词条"))
if result:
   print(result) # 百度这个碧池在最后加了个“符号，给它去掉
   return False
else:
   return True

def summary(soup):
word = soup.h1.text
# 如果存在副标题，一起打印
if soup.h2:
   word += soup.h2.text
# 打印标题
print(word)
# 打印简介
if soup.find(class_="lemma-summary"):
   print(soup.find(class_="lemma-summary").text)

def get_urls(soup):
for each in soup.find_all(href=re.compile("view")):
   content = ''.join()

   url2 = ''.join(["http://baike.baidu.com", each["href"]])

   response2 = urllib.request.urlopen(url2)
   html2 = response2.read()
   soup2 = BeautifulSoup(html2, "html.parser")
   if soup2.h2:
         content = ''.join()
   content = ''.join()
   yield content


def main():
word = input("请输入关键词：")
keyword = urllib.parse.urlencode({"word":word})
response = urllib.request.urlopen("https://baike.baidu.com/search/word?%s" % keyword)
html = response.read()
soup = BeautifulSoup(html, "html.parser")

if test_url(soup):
   summary(soup)

   print("下边打印相关链接：")
   each = get_urls(soup)
   while True:
         try:
            for i in range(10):
               print(next(each))
         except StopIteration:
            break

         command = input("输入任意字符将继续打印，q退出程序：")
         if command == 'q':
            break
         else:
            continue

if __name__ == "__main__":
main()

zltzlt 发表于 2020-3-29 08:11:49

报的什么错？

fresh_python 发表于 2020-3-29 08:48:31

zltzlt 发表于 2020-3-29 08:11
报的什么错？

Traceback (most recent call last):
File "C:\Users\xiha\AppData\Local\Programs\Python\Python37-32\baidu.py", line 101, in <module>
main()
File "C:\Users\xiha\AppData\Local\Programs\Python\Python37-32\baidu.py", line 90, in main
print(next(each))
File "C:\Users\xiha\AppData\Local\Programs\Python\Python37-32\baidu.py", line 66, in get_urls
response2 = urllib.request.urlopen(url2)
File "C:\Users\xiha\AppData\Local\Programs\Python\Python37-32\lib\urllib\request.py", line 222, in urlopen
return opener.open(url, data, timeout)
File "C:\Users\xiha\AppData\Local\Programs\Python\Python37-32\lib\urllib\request.py", line 525, in open
response = self._open(req, data)
File "C:\Users\xiha\AppData\Local\Programs\Python\Python37-32\lib\urllib\request.py", line 543, in _open
'_open', req)
File "C:\Users\xiha\AppData\Local\Programs\Python\Python37-32\lib\urllib\request.py", line 503, in _call_chain
result = func(*args)
File "C:\Users\xiha\AppData\Local\Programs\Python\Python37-32\lib\urllib\request.py", line 1345, in http_open
return self.do_open(http.client.HTTPConnection, req)
File "C:\Users\xiha\AppData\Local\Programs\Python\Python37-32\lib\urllib\request.py", line 1317, in do_open
encode_chunked=req.has_header('Transfer-encoding'))
File "C:\Users\xiha\AppData\Local\Programs\Python\Python37-32\lib\http\client.py", line 1244, in request
self._send_request(method, url, body, headers, encode_chunked)
File "C:\Users\xiha\AppData\Local\Programs\Python\Python37-32\lib\http\client.py", line 1255, in _send_request
self.putrequest(method, url, **skips)
File "C:\Users\xiha\AppData\Local\Programs\Python\Python37-32\lib\http\client.py", line 1122, in putrequest
self._output(request.encode('ascii'))
UnicodeEncodeError: 'ascii' codec can't encode characters in position 36-39: ordinal not in range(128)
>>>

Chysial 发表于 2020-3-29 10:02:14

原来小甲鱼写的时候没有link里边有中文的连接，后边有中文的连接了，所以不行，把他那个keyword在url2哪里输一遍，把汉字编码就好了，改一下就okl了
mport urllib.request
import urllib.parse
import re
from bs4 import BeautifulSoup

def test_url(soup):
result = soup.find(text=re.compile("百度百科尚未收录词条"))
if result:
   print(result) # 百度这个碧池在最后加了个“符号，给它去掉
   return False
else:
   return True

def summary(soup):
word = soup.h1.text
# 如果存在副标题，一起打印
if soup.h2:
   word += soup.h2.text
# 打印标题
print(word)
# 打印简介
if soup.find(class_="lemma-summary"):
   print(soup.find(class_="lemma-summary").text)

def get_urls(soup):
for each in soup.find_all(href=re.compile("view")):
   content = ''.join()
   print(each.text)
   if '=' in each['href']:

         = each['href'].split('Name=',2)
         keyname = urllib.parse.urlencode({"Name":name})
         key_link = links + keyname
   else:
         key_link = each['href']
   url2 = ''.join(["http://baike.baidu.com", key_link])
   response2 = urllib.request.urlopen(url2)
   html2 = response2.read()
   soup2 = BeautifulSoup(html2, "html.parser")
   if soup2.h2:
         content = ''.join()
   content = ''.join()
   yield content


def main():
word = input("请输入关键词：")
keyword = urllib.parse.urlencode({"word":word})
response = urllib.request.urlopen("https://baike.baidu.com/search/word?%s" % keyword)
html = response.read()
soup = BeautifulSoup(html, "html.parser")

if test_url(soup):
   summary(soup)

   print("下边打印相关链接：")
   each = get_urls(soup)
   while True:
         try:
            for i in range(10):
               print(next(each))
         except StopIteration:
            break

         command = input("输入任意字符将继续打印，q退出程序：")
         if command == 'q':
            break
         else:
            continue

if __name__ == "__main__":
main()

这是结果：
请输入关键词：tom
汤姆（美国动画片《猫和老鼠》中的主角）

汤姆（Tom）是米高梅公司制作的经典动画片《猫和老鼠》中的主角之一，70年代老动画中的著名卡通明星角色，是一只蓝灰和白色混合的英国短毛猫。他与小老鼠杰瑞（Jerry）之间可称得上是一对欢喜冤家，二者亦敌亦友，有时互相捣乱，有时互相帮助，有时争论不休，有时团结和谐。他每天忙碌于捉住同住在一起的杰瑞，但总是不如意，总在被耍，憨傻得可爱。生活中充满幽默搞笑，同时也具有抒情与伤情的一幕；主人通常都为两只鞋太太（又黑又胖的女人）。另外，他也爱慕漂亮的千金母猫图多盖洛。有时还被其他成员欺负，如斯派克（Spike）、布奇、莱特宁、托普斯等。

下边打印相关链接：
恐龙百科
恐龙百科 -> http://baike.baidu.com/wikicategory/view?categoryName=%E6%81%90%E9%BE%99%E5%A4%A7%E5%85%A8
多肉百科
多肉百科 -> http://baike.baidu.com/wikicategory/view?categoryName=%E5%A4%9A%E8%82%89%E6%A4%8D%E7%89%A9
里约残奥会吉祥物
里约残奥会吉祥物（里约残奥会吉祥物） -> http://baike.baidu.com/item/TOM/19885318#viewPageContent
名字
名字（名字） -> http://baike.baidu.com/item/TOM/2044473#viewPageContent
全面订单管理
全面订单管理（全面订单管理） -> http://baike.baidu.com/item/TOM/2044457#viewPageContent
移动互联网公司
移动互联网公司（移动互联网公司） -> http://baike.baidu.com/item/TOM/39488#viewPageContent
化学术语
化学术语（化学术语） -> http://baike.baidu.com/item/TOM/2044489#viewPageContent
同义词
同义词目录 -> http://baike.baidu.com/subview/71844/10028254.htm
我感觉小甲鱼哪个href少了半个引号的，所以有的网址好像不太对你自己调试把我就不改了

fresh_python 发表于 2020-3-29 10:52:47

我后来改成这样，就不报错了{:10_266:}
import urllib.request
import urllib.parse
import re
from bs4 import BeautifulSoup

def test_url(soup):
result = soup.find(text=re.compile("百度百科尚未收录词条"))
if result:
   print(result) # 百度这个碧池在最后加了个“符号，给它去掉
   return False
else:
   return True

def summary(soup):
word = soup.h1.text
# 如果存在副标题，一起打印
if soup.h2:
   word += soup.h2.text
# 打印标题
print(word)
# 打印简介
if soup.find(class_="lemma-summary"):
   print(soup.find(class_="lemma-summary").text)

def get_urls(soup):
for each in soup.find_all(href=re.compile("view")):

   content = ''.join()

   url2 = ''.join(["http://baike.baidu.com", each["href"]])
   try:
         response2 = urllib.request.urlopen(url2)
         html2 = response2.read()
         soup2 = BeautifulSoup(html2, "html.parser")
         if soup2.h2:
            content = ''.join()
         content = ''.join()
         yield content
   except:
         pass



def main():
word = input("请输入关键词：")
keyword = urllib.parse.urlencode({"word":word})
response = urllib.request.urlopen("https://baike.baidu.com/search/word?%s" % keyword)
html = response.read()
soup = BeautifulSoup(html, "html.parser")

if test_url(soup):
   summary(soup)

   print("下边打印相关链接：")
   each = get_urls(soup)
   while True:
         try:
            for i in range(10):
               print(next(each))
         except StopIteration:
            break

         command = input("输入任意字符将继续打印，q退出程序：")
         if command == 'q':
            break
         else:
            continue

if __name__ == "__main__":
main()

fresh_python 发表于 2020-3-29 10:55:02

Chysial 发表于 2020-3-29 10:02
原来小甲鱼写的时候没有link里边有中文的连接，后边有中文的连接了，所以不行，把他那个keyword在url2哪里 ...

感谢

Chysial 发表于 2020-3-29 14:38:51

fresh_python 发表于 2020-3-29 10:52
我后来改成这样，就不报错了

是不报错了，把部分给删了也能用

页: [1]

鱼C论坛's Archiver

python 55讲的课后作业