为什么我无法在 Python 中抓取此链接？

Question

我正在尝试抓取网页的内容，但我不明白为什么会出现此错误：http.client.IncompleteRead: IncompleteRead(2268 bytes read, 612 more expected)

这是我要抓取的链接： www.rc2.vd.ch

这是我用来抓取的 Python 代码：

import requests
from bs4 import BeautifulSoup
def spider_list():
    url = 'http://www.rc2.vd.ch/registres/hrcintapp-pub/companySearch.action?lang=FR&init=false&advancedMode=false&printMode=false&ofpCriteria=N&actualDate=18.08.2015&rowMin=0&rowMax=0&listSize=0&go=none&showHeader=false&companyName=&companyNameSearchType=CONTAIN&companyOfsUid=&companyOfrcId13Part1=&companyOfrcId13Part2=&companyOfrcId13Part3=&limitResultCompanyActive=ACTIVE&searchRows=51&resultFormat=STD_COMP_NAME&display=Rechercher#result'

    source_code = requests.get(url)
    plain_text = source_code.text
    soup = BeautifulSoup(plain_text, 'html.parser')

    for link in soup.findAll('a', {'class': 'hoverable'}):
        print(link)

spider_list()

我尝试了另一个网站链接，它工作正常，但为什么我不能抓取这个？

如果无法使用此代码执行此操作，我该怎么做？

------------ 编辑 ------------

这是完整的错误信息：

    Traceback (most recent call last):
  File "C:/Users/Nuriddin/PycharmProjects/project/a.py", line 19, in <module>
    spider_list()
  File "C:/Users/Nuriddin/PycharmProjects/project/a.py", line 12, in spider_list
    source_code = requests.get(url)
  File "C:\Python34\lib\site-packages\requests\api.py", line 69, in get
    return request('get', url, params=params, **kwargs)
  File "C:\Python34\lib\site-packages\requests\api.py", line 50, in request
    response = session.request(method=method, url=url, **kwargs)
  File "C:\Python34\lib\site-packages\requests\sessions.py", line 465, in request
    resp = self.send(prep, **send_kwargs)
  File "C:\Python34\lib\site-packages\requests\sessions.py", line 605, in send
    r.content
  File "C:\Python34\lib\site-packages\requests\models.py", line 750, in content
    self._content = bytes().join(self.iter_content(CONTENT_CHUNK_SIZE)) or bytes()
  File "C:\Python34\lib\site-packages\requests\models.py", line 673, in generate
    for chunk in self.raw.stream(chunk_size, decode_content=True):
  File "C:\Python34\lib\site-packages\requests\packages\urllib3\response.py", line 303, in stream
    for line in self.read_chunked(amt, decode_content=decode_content):
  File "C:\Python34\lib\site-packages\requests\packages\urllib3\response.py", line 450, in read_chunked
    chunk = self._handle_chunk(amt)
  File "C:\Python34\lib\site-packages\requests\packages\urllib3\response.py", line 420, in _handle_chunk
    returned_chunk = self._fp._safe_read(self.chunk_left)
  File "C:\Python34\lib\http\client.py", line 664, in _safe_read
    raise IncompleteRead(b''.join(s), amt)
http.client.IncompleteRead: IncompleteRead(4485 bytes read, 628 more expected)

Answer 1

可能你的编辑器有问题。

我在 python 3 中得到正确的结果，您的代码在 IDLE。

下面附上图片供参考-

我唯一能想到的就是以某种方式绕过错误：

import requests
from bs4 import BeautifulSoup
def spider_list():
    url = 'http://www.rc2.vd.ch/registres/hrcintapp-pub/companySearch.action?lang=FR&init=false&advancedMode=false&printMode=false&ofpCriteria=N&actualDate=18.08.2015&rowMin=0&rowMax=0&listSize=0&go=none&showHeader=false&companyName=&companyNameSearchType=CONTAIN&companyOfsUid=&companyOfrcId13Part1=&companyOfrcId13Part2=&companyOfrcId13Part3=&limitResultCompanyActive=ACTIVE&searchRows=51&resultFormat=STD_COMP_NAME&display=Rechercher#result'
    try:
        source_code = requests.get(url)
        plain_text = source_code.text
        soup = BeautifulSoup(plain_text, 'html.parser')

        for link in soup.findAll('a', {'class': 'hoverable'}):
            print(link)
    except:
        pass
        #I am passing but you do whatever you want to do in case of error
spider_list()

如果有帮助，请告诉我。

Answer 2

这个怎么样！！

import requests
from lxml.html import fromstring

url = 'https://www.rc2.vd.ch/registres/hrcintapp-pub/companySearch.action?lang=FR&init=false&advancedMode=false&printMode=false&ofpCriteria=N&actualDate=18.08.2015&rowMin=0&rowMax=0&listSize=0&go=none&showHeader=false&companyName=&companyNameSearchType=CONTAIN&companyOfsUid=&companyOfrcId13Part1=&companyOfrcId13Part2=&companyOfrcId13Part3=&limitResultCompanyActive=ACTIVE&searchRows=51&resultFormat=STD_COMP_NAME&display=Rechercher#result'

def spider_list(link):
    code = requests.get(link)
    tree = fromstring(code.text)
    skim = tree.xpath('//a[@class="hoverable"]/@href')
    print(skim)

if __name__ == '__main__':
    spider_list(url)