爬取腾讯/爱奇艺视频80年代所有喜剧电影并写入excle表格

腾讯视频
import requests
import xlwt
import re
file = xlwt.Workbook(encoding = 'utf-8')
sheet = file.add_sheet('汇总表')
sheet.write(0,0,'影片名')
sheet.write(0,1,'评分')
sheet.write(0,2,'主演')
sheet.write(0,3,'影片链接')
response = requests.get('https://v.qq.com/')
#print(response.text)
result = re.findall('<a href="(.*?)" data-key="电影" ',response.text)
#print(result)
detail = 'https://v.qq.com' + result[0]
#print(detail)
response = requests.get(detail)
#print(response.text)
result = re.findall('<a href="(.*?)" data-value="itype=100004"',response.text)
#print(result)
detail = 'https://v.qq.com' + result[0]
#print(detail)
response = requests.get(detail)
#print(response.text)
result = re.findall('<a href="(.*?)" class="filter_item "  data-key="year" data-value="100039"',response.text)
#print(result)
detail = result[0]
#print(detail)
response = requests.get(detail)
#print(response.text)
#response1 = response
#response1.encoding = 'utf-8'
result = re.findall('<a href="(.*?)amp;(.*?)&amp;itype=100004"',response.text)
#print(result)
i = 0
k = 0
l = 1
w = 1
detail1 = detail
result1 =result
while i < 300:
    detail = detail1 + result1[0][0][12] + 'itype=100004&' + result1[0][1][0:7] + str(i)
    i = i + 30
    #print(detail)
    response = requests.get(detail)
    #print(response.text)
    result = re.findall('<strong class="figure_title"><a href="(.*?)"',response.text)
    actor = re.findall('''主演：(.*?)</div>''',response.text,re.S)
    j = 0
    for a in actor:
        actor = re.findall('title="(.*?)"',a,re.S)
        print(actor)
        for b in actor:
            actor[j] = b + '    '
            j = j + 1
        j = 0
        sheet.write(w,2,actor)
        w = w + 1
        if w == 194 :
            w = w + 1
    title =  re.findall('alt="(.*?)" r-imgerr="v">',response.text)
    score1 = re.findall('<em class="score_l">(.*?)</em>',response.text)
    score2 = re.findall('<em class="score_s">(.*?)</em>',response.text)
    score = [score1[k] + score2[k] for k in range(min(len(score1),len(score2)))]
    #print(result)
    #print(title)
    #print(score)
    for titl in title:
        print('{:u3000<18}{:u3000>10}{:u3000>50}'.format(titl,score[j],result[j]))
        #response1 = requests.get(result[j])
        sheet.write(l,0,titl)
        sheet.write(l,1,score[j])
        sheet.write(l,3,result[j])
        j = j + 1
        l = l + 1
file.save('80年代喜剧电影.xls')

爱奇艺
import requests
import xlwt
import re
j = 1
m = 0
n = 1
file = xlwt.Workbook('80年代喜剧电影')
sheet1 = file.add_sheet('汇总表')
sheet1.write(0, 0, 'video_name')
sheet1.write(0, 1, 'score')
sheet1.write(0, 2, 'link')
while j < 8:
    url = 'https://list.iqiyi.com/www/1/8-----------1980_1989--11-' + str(j) + '-1-iqiyi--.html'
    response = requests.get(url)
    # print(response.text)
    detail = re.findall('class="qy-mod-link" href="(.*?)" target="_blank"', response.text)
    score = re.findall('<span class="text-score">(.*?)</span>', response.text)
    video_name = re.findall('<img alt="(.*?)"', response.text)
    # print(score)
    # print(video_name)
    # print(detail)
    # for i,d in enumerate(detail):
    # detail[i] = 'https:' + d
    for i in range(len(detail)):
        detail[i] = 'https:' + detail[i]
    for i in detail:
        print(video_name[m], '   ', score[m], '    ', i)
        sheet1.write(n, 0, video_name[m])
        sheet1.write(n, 1, score[m])
        sheet1.write(n, 2, i)
        m = m + 1
        n = n + 1
    j = j + 1
    m = 0
# print(detail)
file.save('爱奇艺80年代喜剧电影.xls')