Python -- 网络编程 -- 简单抓取网页

抓取网页:　　urllib.request.urlopen(url).read().decode('utf-8') --- (百度是utf-8,谷歌不是utf-8，也不是cp936，ascii也不行，iso-8859-1勉强)

PyQt4.QtGui的QTextEdit控件自动解析HTML文档，为显示纯HTML文件，应使用方法QTextEdit.setPlainText()

例：抓取网页的标题、图片和链接

import sys, re
import urllib.request
from PyQt4 import QtGui

class MainWindow(QtGui.QWidget):
def __init__(self):
super(MainWindow, self).__init__()
self.setWindowTitle('Crawl')
self.resize(485, 300)

self.txt = QtGui.QTextEdit()
#         self.txt.setF
self.txt.setReadOnly(True)

grid = QtGui.QGridLayout()
grid.addWidget(self.txt)
self.setLayout(grid)

url = 'http://www.baidu.com/s?wd=python'
page = urllib.request.urlopen(url).read().decode('utf-8')
fp = open('e:/temp.txt', 'wt', encoding='utf-8')
fp.write(page)
fp.close

s = '标题：\n'
page_title = re.compile('<title>(.+?)</title>')
s += page_title.findall(page)[0]+'\n'

s += '图片：\n'
page_images = re.compile('<img src="(.+?)"')
for data in page_images.findall(page):
s += data+'\n'

s += '链接：\n'
page_link = re.compile('href="(.+?)"')
for data in page_link.findall(page):
s += data+'\n'

self.txt.setPlainText(s)

app = QtGui.QApplication(sys.argv)
mainwindow = MainWindow()
mainwindow.show()

app.exec_()