st4lk

import csv
import logging

def get_csv_lines(file_name, encoding='cp1251'):
    try:
        lines = []
        with open(file_name, 'rb') as f:
            reader = csv.reader(f, delimiter=";")
            for line in reader:
                decoded_line = []

st4lk

(?<=<h2>).+(?=</h2>)

st4lk

from xlrd import open_workbook
from xlutils.copy import copy

def save_workbook_copy(file_from, file_to):
    rb = open_workbook(file_from, formatting_info=True)
    wb = copy(rb)  # a writable copy (I can't read values out of this, only write to it)
    w_sheet = wb.get_sheet(0)  # the sheet to write to within the writable copy
    row_index = 0
    col_index = 0
    w_sheet.write(row_index, col_index,'DataToBeWritten')

st4lk

from xlrd import open_workbook


def is_row_hidden(sheet, row_n):
    try:
        if sheet.rowinfo_map[row_n].hidden:
            return True
    except KeyError:
        #  empty row, treat as hidden
        pass

st4lk

from config import Session
from models import Person

session = Session()
persons = session.query(Person).filter(Person.name == u"Василий Пупкин", Person.status == STATUS.employer)
persons = session.query(Person).filter(Person.info.like(u"%Веб%"))
for person in persons:
    print person.link

st4lk

import pickle

with open('data.pkl', 'wb') as output:
    pickle.dump(data1, output)
    pickle.dump(data2, output)

with open('data.pkl', 'rb') as pkl_file:
    data1 = pickle.load(pkl_file)
    data2 = pickle.load(pkl_file)

st4lk

python setup.py install
paster create --template=spider site.ru
paster create --list-templates

st4lk

# xpath contains
u'//div[@class="rules"]/div[@class="inner"][contains(./div/text(), "Фотографии не найдены")]'

# xpath 'and' end 'exact'
u'//div[@id="accordion"]/table//tr[./td[1]/text()="SHAPE" and ./td[2]/text()="CARATS"]'

# xpath subling
root_elem.xpath('./following-sibling::*')

# xpath parent

st4lk

class OrderedSet(collections.MutableSet):

    def __init__(self, iterable=None):
        self.end = end = []
        end += [None, end, end]         # sentinel node for doubly linked list
        self.map = {}                   # key --> [key, prev, next]
        if iterable is not None:
            self |= iterable

    def __len__(self):

st4lk

1)Создание базы для Django:
CREATE DATABASE database_name CHARACTER SET utf8;
CREATE USER 'user_name'@'localhost' IDENTIFIED BY 'user_password';
GRANT ALL ON database_name.* TO 'user_name'@'localhost';
2) Дамп базы
Сохранение: mysqldump -u имя_пользователя -p -h имя_сервера_БД имя_базы > dump.sql
Восстановление: mysql -u имя_пользователя -p -h имя_сервера_БД имя_базы < dump.sql