python 百度貼吧

#encoding=utf8
from bs4 import BeautifulSoup
import requests
import time
import random
import xlwt


flag = ''
getin = ''
c= 0
def detailOper(url, params, header, timeout = 10):
    global flag
    out = []
    web_data = requests.get(url, params=params, headers=header, timeout=timeout)
    soup = BeautifulSoup(web_data.text, 'lxml')
    titles = soup.select(
        '#thread_list > li > div > div.col2_right.j_threadlist_li_right > div.threadlist_lz.clearfix > div.threadlist_title.pull_left.j_th_tit > a')
    authors = soup.select(
        '#thread_list > li > div > div.col2_right.j_threadlist_li_right > div.threadlist_lz.clearfix > div.threadlist_author.pull_right > span.tb_icon_author > span.frs-author-name-wrap > a')
    回帖數量 = soup.select('#thread_list > li > div > div.col2_left.j_threadlist_li_left > span')
    button = soup.select('#frs_list_pager > a.next.pagination-item')

    for title, authors, 回帖數量 in zip(titles, authors, 回帖數量):
        detailurl = str('https://tieba.baidu.com'+str(title.get('href')))
        data = {
            'title': title.get_text(),
            'link': detailurl,
            'author': authors.get_text(),
            'floor': 回帖數量.get_text(),
        }
        out.append(data)
    print(out)
    if not out:
        print(web_data.status_code)
        return 'no data'
    elif not button:
        flag = 'end'
    return out

page = 0
name = input('input name:')
wrongpage = []
data = []
UA = [
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
    "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
    "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
    "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
    "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
    "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
    "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
    "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
    "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; 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; LBBROWSER)",
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 LBBROWSER",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; 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)",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; 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; QQBrowser/7.0.3698.400)",
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; 360SE)",
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; 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)",
    "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
    "Mozilla/5.0 (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 Safari/6533.18.5",
    "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0b13pre) Gecko/20110307 Firefox/4.0b13pre",
    "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:16.0) Gecko/20100101 Firefox/16.0",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11",
    "Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10"
]
headers = {}

while True:
    params = {'kw': name, 'ie': 'utf-8', 'pn': page}
    headers['User-Agent'] = random.choice(UA)
    try:
        d = detailOper('https://tieba.baidu.com/f', params=params, header=headers)
        if flag == 'end':
            print('that\'s the end, total %s page.' % (page/50+1))
            break
        if d == 'no data':
            wrongpage.append(page)
            print('wrong')
            page += 50
            continue
        for x in d:
            x['page'] = page/50+1
            data.append(x)
            print(x)
        page += 50
    except:
        wrongpage.append(page)
        page += 50
print(wrongpage)
while True:
    try:
        if not wrongpage:
            break
        page = random.choice(wrongpage)
        params['pn'] = page
        headers['User-Agent'] = random.choice(UA)
        d = detailOper('https://tieba.baidu.com/f', params=params, header=headers)
        if d == 'no data':
            print('still can\'t get page %s' % (page/50+1))
            continue
        wrongpage.remove(page)
        for x in d:
            x['page'] = page/50+1
            data.append(x)
        print(d)
        print(wrongpage)
    except:
        print('time out.')


workbook = xlwt.Workbook(encoding='utf-8')
sheet = workbook.add_sheet('%s' % name)
sheet.write(0, 1, 'title')
sheet.write(0, 2, 'author')
sheet.write(0, 3, 'floor')
sheet.write(0, 4, 'link')


for findata in data:
    c += 1
    sheet.write(c, 0, c)
    sheet.write(c, 1, findata['title'])
    sheet.write(c, 2, findata['author'])
    sheet.write(c, 3, int(findata['floor']))
    sheet.write(c, 4, findata['link'])
workbook.save('%s.xls' % name)




with open('%s.txt' % name, 'a')as file:
    for x in data:
        file.write(str(x))
        file.write('\r')