Python提交表单并处理返回结果

1、将本地文件内容批量提交到指定网址，并将结果保存到本地

import urllib 
import urllib2
import cookielib


cj = cookielib.LWPCookieJar()
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
urllib2.install_opener(opener)


file = open("D://test.final.pdb.fas")#本地文件内容
url = 'http://scansite.mit.edu/cgi-bin/motifscan_seq'#注意是action不是网址
linen = file.readline()#读取文件的一行
lines = file.readline()


while linen:
    values ={'protein_id':linen,#提交表单的内容<input name="protein_id" vaule=""/>
         'sequence':lines,
         'motif_option':'all',
         'stringency':'High'}
    data = urllib.urlencode(values)#发送数据
    req = urllib2.Request(url,data)
    response = opener.open(req)
    fd = response.read()#读取返回结果
    linen = linen.strip('\n')#删除结尾的\n

    linen = linen.strip('>')

    file_object = open('D://'+linen+'.html','w')#写入D的文件
    file_object.write(fd)
    file_object.close()
    linen = file.readline()
    lines = file.readline()
 
file.close()

2、提取网页信息并进行处理

import re


file = open("D://name.txt")  
file_object = open('D://1.txt','w')


line = file.readline()
while line:
    line=line.strip('\n')
    file_object.write(line)
    print line
    filehtml = open("D://"+line+".html")
    linetxt = filehtml.readline()
    while(linetxt):
        foundresult = re.search('site=(?P<site>[a-zA-Z]\d+)&position=\d+&score=(?P<score>\d+.\d+)',linetxt) #re.search只能找一行的，re.findall可以找多行，返回一个数据集
        if(foundresult):
            print foundresult.group("site")+foundresult.group("score")
            file_object.write('\t'+foundresult.group("site")+'\t'+foundresult.group("score"))
        linetxt = filehtml.readline()        
    file_object.write('\n')
    line = file.readline()
    filehtml.close()
    
file_object.close() 
file.close()

3、补充

（1）读取文件

file = open("D://test.final.pdb.fas")
line = file.readline()
while line:
    print line,
    line = file.readline()
    
file.close()

（2）读取数据集中的每项数据的名称

file = open("D://test.final.pdb.fas")
file_object = open('D://name.txt','w')
line = file.readline()
while line:
    line = line.strip('>')
    file_object.write(line)
    line = file.readline()
    line = file.readline()
    
file_object.close()
file.close()

（3）re.findall()的处理

import urllib 
import urllib2
import cookielib
import re


cj = cookielib.LWPCookieJar()
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
urllib2.install_opener(opener)


file = open("D://test.final.pdb.fas")  
file_object = open('D://1.txt','w')
url = 'http://scansite.mit.edu/cgi-bin/motifscan_seq'
linen = file.readline()
lines = file.readline()
while linen:
    values ={'protein_id':linen,
         'sequence':lines,
         'motif_option':'all',
         'stringency':'High'}
    data = urllib.urlencode(values)
    req = urllib2.Request(url,data)
    response = opener.open(req)
    fd = response.read()
    linen = linen.strip('\n')
    linen = linen.strip('>')
    file_object.write(linen)
    found = re.findall('site=[a-zA-Z]\d+&position=\d+&score=\d+.\d+',fd)
    #print found
    if(found):
        for i in found:
            foundresult = re.search('site=(?P<site>[a-zA-Z]\d+)&position=\d+&score=(?P<score>\d+.\d+)',i)
            print foundresult.group("site")+foundresult.group("score")
            file_object.write('\t'+foundresult.group("site")+'\t'+foundresult.group("score"))


            
    file_object.write('\n')
    linen = file.readline()
    lines = file.readline()
    
file_object.close() 
file.close()

入门学习连接：

python 自动填写表单xml解析： http://blog.chinaunix.net/uid-22340094-id-3059345.html

保存内容到本地 ： http://jingyan.baidu.com/article/ed2a5d1f1b78ff09f6be178f.html

逐行读取文件 ： http://www.cnblogs.com/sysuoyj/archive/2012/03/14/2395789.html