我不是编码员,我需要完成的只是获得一个完整的源代码。我不久前发现了这段代码,它一直很好用。但由于定时器的广告分层,它对某些网站起作用了。
{
"Report" : {
"-Kpne6Xp29_MkkB_-aPA" : {
"date" : "Jul 24, 4:14 PM",
"desc" : "bubble gum",
"image" : "https://firebasestorage.googleapis.com/v0/b/report-f7656.appspot.com/o/Material%2Fcropped620487630.jpg?alt=media&token=e63a7fd8-b7ed-4277-9709-f5182f2db71d",
"name" : "kenzo",
"title" : "ditto",
"type" : "Material",
"uid" : "7DxLHiNhUUYwPTKnRx0ylJ2O8zb2"
},
"-Kpnj6Dm0uO_YR3qrB0V" : {
"date" : "Jul 24, 4:36 PM",
"desc" : "insta story",
"image" : "https://firebasestorage.googleapis.com/v0/b/report-f7656.appspot.com/o/Material%2Fcropped2010735531.jpg?alt=media&token=940fedda-4333-4146-9a3f-a891a5ca412c",
"name" : "kenzo",
"title" : "ddlovato",
"type" : "Material",
"uid" : "7DxLHiNhUUYwPTKnRx0ylJ2O8zb2"
}
},
"Users" : {
"7DxLHiNhUUYwPTKnRx0ylJ2O8zb2" : {
"name" : "kenzo"
}
}
}
但是我在Python 2.7控制台中打印出这个
import urllib2,cookielib
site= "http://example.com" #real url edited out
hdr = {'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.3',
'Accept-Encoding': 'none',
'Accept-Language': 'en-US,en;q=0.8',
'Connection': 'keep-alive'}
req = urllib2.Request(site, headers=hdr)
try:
page = urllib2.urlopen(req)
except urllib2.HTTPError, e:
print e.fp.read()
content = page.read()
print content
答案 0 :(得分:0)
我做的是转换成一个函数,它可以工作!!!
def getHtml(url):
import urllib2,cookielib
hdr = {'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11',
'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.3',
'Accept-Encoding': 'none',
'Accept-Language': 'en-US,en;q=0.8',
'Connection': 'keep-alive',
'Content-Type': 'application/x-www-form-urlencoded'}
req = urllib2.Request(url, headers=hdr)
try:
page = urllib2.urlopen(req)
except urllib2.HTTPError, e:
print e.fp.read()
html = page.read()
#print html
return html;
替代(慢),当我在互联网上看时,我发现你可以使用Python Selenium WebDriver使用Firefox或Chrome或Headless PhantomJS来获取html源代码。您需要在C:\ Python27 \ Scripts \
中放置GeckoDriver.exe或ChromeDriver.exe或PhantomJS.exedef getHtmlViaWebDriver(url):
from selenium import webdriver
#print("Open Web Driver - External Head/less Browser PhantomJS or Firefox or Chrome")
#driver = webdriver.Firefox(executable_path=r'C:\Python27\Scripts\geckodriver.exe')
#driver = webdriver.Chrome(executable_path=r'C:\Python27\Scripts\chromedriver.exe')
driver = webdriver.PhantomJS(executable_path=r'C:\Python27\Scripts\phantomJS.exe')
html = driver.page_source.encode('utf-8')
driver.quit()
#print html
return html;