Question

我试图抓一些网页内容。虽然脚本在spyder python控制台（而不是ipython控制台）中运行正常，但在windows cmd行中运行时会抛出错误。

from PyQt4.QtGui import *
from PyQt4.QtCore import *
from PyQt4.QtWebKit import *
from bs4 import BeautifulSoup

class Render(QWebPage):
    def __init__(self, url):
        self.app = QApplication(sys.argv)
        QWebPage.__init__(self)
    self.loadFinished.connect(self._loadFinished)
    self.mainFrame().load(QUrl(url))
    self.app.exec_()

def _loadFinished(self, result):
    self.frame = self.mainFrame()
    self.app.quit()

url = "http://www.shfe.com.cn/en/MarketData/dataview.html?paramid=dailystock"
r = Render(url)
result = r.frame.toHtml()
soup = BeautifulSoup(result, 'lxml')

这是错误消息

soup = BeautifulSoup(result, 'lxml')
File "C:\Anaconda2\lib\site-packages\bs4\__init__.py", line 225, in __init__
markup, from_encoding, exclude_encodings=exclude_encodings)):
File "C:\Anaconda2\lib\site-packages\bs4\builder\_lxml.py", line 118, in prepare_markup
for encoding in detector.encodings:
File "C:\Anaconda2\lib\site-packages\bs4\dammit.py", line 257, in encodings
self.markup, self.is_html)
File "C:\Anaconda2\lib\site-packages\bs4\dammit.py", line 319, in find_declared_encoding
declared_encoding = declared_encoding_match.groups()[0].decode(
AttributeError: 'QString' object has no attribute 'decode'

Python 2.7.13 | Anaconda custom（32位）| （默认情况下，2016年12月19日，13：36：02）[win v300 32位（英特尔）]在win32上

python，脚本在spyder中运行但不在控制台中，BeautifulSoup失败

0 个答案: