#!/usr/bin/env/ python
#coding:utf8
import requests
from bs4 import BeautifulSoup
url = "http://butian.360.cn/company/lists/page/"
def getMaxPageNumber(content):
soup = BeautifulSoup(content, "html.parser")
divs = soup.find("div", class_="pages")
as_ = divs.findAll("a")
pages_text = as_[-1].get("href")
return int(pages_text.split("/")[-1])
def getWebSites(content):
results = []
soup = BeautifulSoup(content, "html.parser")
trs = soup.findAll("tr")
for tr in trs:
tds = tr.findAll('td',align="left",style="padding-left:20px;")
tds = tds[1:]
for td in tds:
url = td.string
result = url
results.append(result)
return results
def getContentOfPage(url):
return requests.get(url).text
maxPageNumber = getMaxPageNumber(getContentOfPage(url + "1"))
for page in range(1,maxPageNumber + 1):
try:
tempURL = url + str(page)
print "Getting : " + tempURL
result = getWebSites(getContentOfPage(tempURL))
outfile = open("websites.txt", "a+")
for res in result:
outfile.write("http://" + res + "/\n")
outfile.close()
except Exception as e:
pass
Python获取补天所有厂商网址
最后编辑于 :
©著作权归作者所有,转载或内容合作请联系作者
- 文/潘晓璐 我一进店门,熙熙楼的掌柜王于贵愁眉苦脸地迎上来,“玉大人,你说我怎么就摊上这事。” “怎么了?”我有些...
- 文/花漫 我一把揭开白布。 她就那样静静地躺着,像睡着了一般。 火红的嫁衣衬着肌肤如雪。 梳的纹丝不乱的头发上,一...
- 文/苍兰香墨 我猛地睁开眼,长吁一口气:“原来是场噩梦啊……” “哼!你这毒妇竟也来了?” 一声冷哼从身侧响起,我...