web crauler

import requests
from bs4 import BeautifulSoup

#link = "https://edition.cnn.com/"
goto =    "https://www.povarenok.ru/recipes/kitchen/77/"
#link = "https://www.povarenok.ru/recipes/show/70127/"

pages = [''] * 13
pages[0] = goto

s = 'https://www.povarenok.ru/recipes/kitchen/77/~2/'
pages[1] = s



for i in range(2, 13):
    s = pages[i - 1]
    s = goto + '~' + str(i + 1) + '/'
    pages[i] = s
print(pages)
"""в конце изменить goto:

"""
#for i in range(13):

names = []
recep = []
photo = []
#<div class="ingredients-bl">
debug = False

def ingrid(goto):
    #print("goto = ", goto)
    html = requests.get(goto)
    html.encoding = 'windows-1251'
    sp = BeautifulSoup(html.text, 'lxml')
    ing = sp.find('div', "ingredients-bl")
    all = ing.find_all('span')
    #print("all")
    #print(all)
    ing_list = []

    for i in range(0, len(all), 2):
        if i + 1 >= len(all):
            break
        one_ing = all[i]
        one_ing = str(one_ing)
        since = one_ing.find('n>') + 2
        till = one_ing.find('</')
        ing_str = one_ing[since: till]
        amount = all[i + 1]
        amount = str(amount)
        since = amount.find('n>') + 2
        till = amount.find('</')
        amount_str = amount[since: till]
        res = ing_str + "  " + amount_str
        ing_list.append(res)
        #print(one_ing, amount)
    #print("ing list")
    #print(ing_list)
    recep.append(ing_list)
    #print(ing)

def work(goto):
    print("WORK")
    html = requests.get(goto)
    html.encoding = 'windows-1251'
    sp = BeautifulSoup(html.text, 'lxml')
    all = sp.find_all('div', "m-img desktop-img conima")
    #print(all)
    for rec in all:
        if debug:
            print("NEW REC")
            print(rec)
        #print(rec)
        raw = rec.find('img')
        #отсюда название и  ссылка на картинку
        #print("IMAGE")
        #print(img)
        raw = str(raw)
        since = raw.find('Ре')
        till = raw.find('src')
        name = raw[since: till]
        names.append(name)

        since = raw.find('htt')
        till = raw.find('/>') - 1
        photo_link = raw[since: till]
        photo.append(photo_link)
        #КАК получить список ингридиентов???
        link = rec.find('a')
        if debug:
            print("link")
            print(link)
            print("end link")
        link = str(link)
        till = link.find(">")
        since = link.find("htt")
        link = link[since: till - 1]
        ingrid(link)
        if debug:
            print("new link")
            print(link)
        #print()
        #print()
        #break




for i in range(13):
    work(pages[i])

print("photo", len(photo))
print(photo)
print("recep", len(recep))
print(recep)
print("names", len(names))
print(names)

import lxml
from xlwt import *
workbook = Workbook(encoding = 'utf-8')
table = workbook.add_sheet('data')
table.write(0, 0, 'Название')
table.write(0, 1, 'Рецепт')
table.write(0, 2, 'Фото')

N = len(recep)
line = 0
for i in range(N):
    line += 1
    table.write(line, 0, names[i])
    table.write(line, 2, photo[i])
    table.write(line, 1, 'ингридиенты')
    for j in range(len(recep[i])):
        line += 1
        table.write(line, 1, recep[i][j])
    line += 1

workbook.save('recep4.xls')
print("FILE SAVED")