很不言自明,试图从Google搜索中做一个小的网页抓取工具,但是当尝试导入时,使用“ var prototype = w.window.Object.getPrototypeOf(input);
console.log(prototype);
”我得到了错误:
ModuleNotFoundError:没有名为“ google”的模块。
当尝试使用“ infile = 'Vendor List.txt'
# Create a generator with differing modes to read the specified lines of the file.
def read_gen(infile, mode=0, start=0, end=0, rows=[]):
lines = list()
with open(infile, 'r') as file:
for i, line in enumerate(file):
# Set end to correct value if no argument is given.
if end == 0:
end = len(line)
# Mode 0 gives all lines of the file
if mode == 0:
yield line[start:end]
# Mode 1 gives specific lines from the file using the rows keyword
# argument. Make sure rows is formatted as [start_row, end_row].
# rows list should only ever be length 2.
elif mode == 1:
if rows:
# Create a list for indices between specified rows.
for element in range(rows[0], rows[1]):
lines += [element]
# Return the current line if the index falls between the
# specified rows.
if i in lines:
yield line[start:end]
class GetAddress:
def __init__(self):
# Allow access to infile for use in set_addresses().
global infile
self.address_indices = list()
self.phone_indices = list()
self.addresses = list()
self.count = 0
def get(self, i, line):
# Search for appropriate substrings and set indices accordingly.
if 'Address:' in line[18:26]:
self.address_indices += [i]
if 'Phone:' in line[18:24]:
self.phone_indices += [i]
# Add address to list if both necessary indices have been collected.
if i in self.phone_indices:
self.set_addresses()
def set_addresses(self):
self.address = list()
start = self.address_indices[self.count]
end = self.phone_indices[self.count]
# Create a generator that only yields substrings for rows between given
# indices.
self.generator = read_gen(
infile,
mode=1,
start=40,
end=91,
rows=[start, end])
# Collect each line of the address from the generator and remove
# unnecessary spaces.
for element in range(start, end):
self.address += [next(self.generator).strip()]
# This document has a header on each page and a portion of that is
# collected in the address substring. Search for the header substring
# and remove the corresponding elements from self.address.
if len(self.address) > 3 and not self.address[-1]:
self.address = self.address[:self.address.index('header text')]
self.addresses += [self.address]
self.count += 1
info = GetAddress()
for i, line in enumerate(read_gen(infile)):
info.get(i, line)
”从命令提示符再次安装google时,出现错误消息:
已经满足要求:from google import search
中的google
已满足要求:pip install google
中的c:\users\dsimard\python\lib\site-packages (2.0.1)
我正在Eclipse中编写该程序。
答案 0 :(得分:0)
尝试from googlesearch import search