Python 爬虫笔记（不定时更新）

#自动访某个网址

from selenium import webdriver
import time
M = 100000 
i = 0
URL = ‘http://www.yyxxww.com/html/2015/edu_0318/3386.html‘
browser = webdriver.Firefox() #浏览器名字，以本机安装为准
while i < M:
    browser.get(URL)
    time.sleep(1)
    i += 1
browser.quit()
print ‘本次python总共打开了‘, i, ‘次‘  


#提取一级标题

import urllib2
from sgmllib import SGMLParser
URL = ‘http://www.yyxxww.com/html/2015/edu_0318/3386.html‘ 
class ListName(SGMLParser):
    def __init__(self):
        SGMLParser.__init__(self)
        self.is_h4 = ""
        self.name = []
    def start_h4(self, attrs):
        self.is_h4 = 1
    def end_h4(self):
        self.is_h4 = ""
    def handle_data(self, text):
        if self.is_h4 == 1:
            self.name.append(text)
 
content = urllib2.urlopen(URL).read()
listname = ListName()
listname.feed(content)
for item in listname.name:
    print item.decode(‘gbk‘).encode(‘utf8‘)    


#访问百度，并填写表单，中文暂时不好解决，英文没问题

# coding = utf-8
import sys
reload(sys)
sys.setdefaultencoding(‘utf8‘)
from selenium import webdriver


browser = webdriver.Firefox()

browser.get("http://www.baidu.com")
browser.find_element_by_id("kw").send_keys("你好").decode(‘gbk‘).encode(‘gb2312‘)
browser.find_element_by_id("su").click()
time.sleep(30)  # 休眠3秒
browser.quit()