def getUrl(url):

response = requests.get(ur)

html = response.text

soup = BeautifulSoup(html, 'html.parser')

main = soup.find_all(class_ = 'db_comtool')#找到所有標(biāo)簽為db_comtool的div里面內(nèi)容

for i in main:

id.append(i.get('blogid'))#將所有blogid的內(nèi)容添加到id這個(gè)列表中

def getArticle(url):

global text

response = requests.get(url)#訪問(wèn)網(wǎng)站

html = response.text#保存網(wǎng)站源代碼

bf = BeautifulSoup(html,'html.parser')#解析網(wǎng)址

a1 = bf.find_all(class_='db_mediacont db_commentcont')#獲取正文文本

a2 = bf.find_all(class_='px38 mt30 c_000')#獲取文章標(biāo)題

for each in a1:

text.append(re.sub('[\t\n]', "", re.sub(r'<[^>]+>', "", str(each))))#利用正則表達(dá)式過(guò)濾掉無(wú)用內(nèi)容

for each in a2:

name = (re.sub('[\t\n]', "", re.sub(r'<[^>]+>', "", str(each))))

f = open('時(shí)光網(wǎng)影評(píng)/%s.txt'%name, 'w') # 首先先創(chuàng)建一個(gè)文件對(duì)象，打開(kāi)方式為w，名字為剛才得到的name

for each in text:

f.writelines(each.encode("gbk", 'ignore').decode("gbk", "ignore")) # 用readlines()方法寫入文件

text = []#清空text

for i in range(1,15):

ur = 'http://movie.mtime.com/11319/comment-{}.html'.format(i)#自動(dòng)翻頁(yè)

getUrl(ur)

for i in id:

url = 'http://movie.mtime.com/11319/reviews/{}.html'.format(i)#自動(dòng)訪問(wèn)每篇影評(píng)的對(duì)應(yīng)地址

getTitle(url)