python 爬虫餐饮行业 数据分析_Python百度爬虫，分析各行业权重排行，数据分析工程师也不如你！-站长资讯中心...

# coding=utf-8

import requests

import re

import sys

reload(sys)

sys.setdefaultencoding('utf-8')

url = "http://top.chinaz.com/all/index_br.html"#由于第一页跟第二页之后的url格式不一样,so,分两步完成.

headers = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36"}

session = requests.session()

html = session.get(url, headers=headers).content

config = re.compile('(.*?).*?(.*?).*?')

res = re.findall(config, html)

connecterror = []

f = open("url.txt", "a")

print '''程序启动... '''

for i in range(1, len(res)):

if "www" in res[0:3]:

cc = "http://" + res[0]

try:

a= cc + ' | Alexa周排名: ' + res[i - 1][1] + ' | 百度权重: ' + res[i - 1][2] + ' | Server: ' + requests.get(cc, headers=headers).headers['Server']

print a

f.write(a+'\n')

except:

a = cc + ' | Alexa周排名: ' + res[i - 1][1] + ' | 百度权重: ' + res[i - 1][2] + ' | Server: 获取失败'

print a

f.write(a+'\n')

connecterror.append(cc)

else:

cc = "http://www." + res[0]

try:

a = cc + ' | Alexa周排名: ' + res[i - 1][1] + ' | 百度权重: ' + res[i - 1][2] + ' | Server: ' + requests.get(cc, headers=headers).headers['Server']

print a

f.write(a+'\n')

except:

a = cc + ' | Alexa周排名: ' + res[i - 1][1] + ' | 百度权重: ' + res[i - 1][2] + ' | Server: 获取失败'

print a

f.write(a+'\n')

connecterror.append(cc)

for j in range(2,1844):

url = "http://top.chinaz.com/all/index_br_%d.html"%j

headers = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36"}

session = requests.session()

html = session.get(url, headers=headers).content

config = re.compile('(.*?).*?(.*?).*?