慧聪网爬虫

import requests
from bs4 import BeautifulSoup
import pandas as pd
import gevent
from gevent import monkey;monkey.patch_all()
import time
import re
import random

UA_list = [
‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36‘
,‘Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/7.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; GWX:MANAGED)‘,‘Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0)‘,‘Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0)‘,‘Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; GWX:MANAGED)‘]

proxies_list=[{‘proxy‘: ‘http:\\10.220.70.254:808‘}, {‘proxy‘: ‘http:\\10.221.70.254:808‘}, {‘proxy‘: ‘http:\\10.222.70.254:808‘}, {‘proxy‘: ‘http:\\10.223.70.254:808‘}]

headers = {‘User-Agent‘:random.choice(UA_list),‘Referer‘:‘http://b2b.hc360.com/‘}

def diyu(sheng,shi):
    for i in range(100):
        or_url = ‘http://s.hc360.com/?w={}&mc=enterprise&ee={}&z=%D6%D0%B9%FA%3A{}%CA%A1%3A{}‘.format(sheng,i+1,sheng,shi)
        res = requests.get(or_url,headers = headers,)
        soup = BeautifulSoup(res.text,‘lxml‘)
        urls = soup.select(‘dd.til > h3 > a‘)
        for url in urls:
            return url.get(‘href‘)

def url_parser(urld):
    res = requests.get(urld, headers=headers,proxies=random.choice(proxies_list),timeout=60)
    if res.status_code !=‘404‘:
        soup = BeautifulSoup(res.text, ‘lxml‘)
        flag = re.findall(r‘公司黄页‘,str(soup))
        if len(flag)>0:
            return url_HYparer(soup)
        else:
            or_url = urld + ‘shop/company.html‘
            res = requests.get(or_url, headers=headers,proxies=random.choice(proxies_list),timeout=60)
            soup1 = BeautifulSoup(res.text, ‘lxml‘)
            flag1 = re.findall(r‘手机极速版‘,str(soup1))
            flag2 = re.findall(r‘未认证 ‘, str(soup1))
            if len(flag1)>0:
                return url_SJJSparer(soup1)
            elif len(flag2)>0:
                return url_uncertifie(soup1)
            else:
                return url_NSJJSparer(soup1)

def url_NSJJSparer(soup):

    data = {
        ‘conpany_name‘:soup.select(‘td.contitlebg > span‘)[0].text.strip(),
        ‘name‘:soup.select(‘span.bluezzbold.font14‘)[0].text.strip(),
        ‘address‘:soup.select(‘td.conbg.conbg2 > ul:nth-of-type(1) > li:nth-of-type(2)‘)[0].get(‘title‘),
        ‘phone‘:re.search(r‘\d{11}|\d{4}-\d{8}‘,str(soup)).group()}
    return data

def url_HYparer(soup):
    data = {
    ‘conpany_name‘:soup.select(‘div.sub-info > h1‘)[0].text,
    ‘name‘:soup.select(‘samp‘)[0].text,
    ‘address‘:soup.select(‘div.tableCon > div:nth-of-type(2) > ul > li:nth-of-type(3) > span.conRight‘)[0].text,
    ‘phone‘:soup.select(‘div.tableCon > div:nth-of-type(2) > ul > li:nth-of-type(2) > span.conRight‘)[0].text
    }
    return data

def url_SJJSparer(soup):
    data = {
        ‘conpany_name‘:soup.select(‘div.ContacCon1 > h3‘)[0].text.strip(),
        ‘name‘:soup.select(‘div.ContactsName > span > a‘)[0].text.strip(),
        ‘address‘:soup.select(‘div.ContacCon3 > ul > li:nth-of-type(1) > div.con3Rig‘)[0].text.strip(),
        ‘phone‘:re.search(r‘\d{11}|\d{4}-\d{8}‘,str(soup)).group()}
    return data

def url_uncertifie(soup):
    data = {
        ‘conpany_name‘:soup.select(‘td.contitlebg_1 > span‘)[0].text.strip(),
        ‘name‘:soup.select(‘span.bluezzbold.font14‘)[0].text.strip(),
        ‘address‘:soup.select(‘td.conbg.conbg2 > ul:nth-of-type(1) > li:nth-of-type(2)‘)[0].text.strip(),
        ‘phone‘:re.search(r‘\d{11}|\d{4}-\d{8}‘,str(soup)).group()}
    return data

if __name__==‘__main__‘:
    with open(‘uu.txt‘, ‘r‘) as f:
        info_total = []
        for i in f:
            try:
                info_ary = url_parser(i.strip())
                time.sleep(random.randint(1,5))
                info_total.append(info_ary)
                print(len(info_total))
            except Exception as e:
                print(e, i.strip())
        df = pd.DataFrame(info_total)
        df.to_excel(‘huicong_beijing.xlsx‘)
        print(‘Done‘)