def query_question(self, question_id):
"""
:rtype: Question_Info
"""
question = DB.query_row(u'select * from Question where question_id in ({question_id})'.format(question_id=question_id))
question = self.format_question(question) # 包装成标准的信息格式
return question
def query_question(self, question_id):
"""
:rtype: Question_Info
"""
question = DB.query_row(u'select * from Question where question_id in ({question_id})'.format(question_id=question_id))
question = self.format_question(question) # 包装成标准的信息格式
return question
def query_answer(self, answer_id):
"""
:type answer_id:int
:return:
"""
answer = DB.query_row(u'select * from Answer where answer_id in ({answer_id})'.format(answer_id=answer_id))
answer = self.format_answer(answer)
return answer
def query_answer_list_by_author_page_id(self, author_page_id):
# 需要先查出来对应的author_id
author_info = DB.query_row(u'select author_id from Author where author_page_id="{author_page_id}"'.format(author_page_id=author_page_id))
author_id = author_info[u'author_id']
raw_answer_list = DB.query_all(u'select * from Answer where author_id="{author_id}" {order_by} '.format(author_id=author_id, order_by=Config.answer_order_by))
answer_list = []
for raw_answer in raw_answer_list:
answer_list.append(self.format_answer(raw_answer))
return answer_list
def query_answer_list_by_author_page_id(self, author_page_id):
# 需要先查出来对应的author_id
author_info = DB.query_row(u'select author_id from Author where author_page_id="{author_page_id}"'.format(author_page_id=author_page_id))
author_id = author_info[u'author_id']
raw_answer_list = DB.query_all(u'select * from Answer where author_id="{author_id}" {order_by} '.format(author_id=author_id, order_by=Config.answer_order_by))
answer_list = []
for raw_answer in raw_answer_list:
answer_list.append(self.format_answer(raw_answer))
return answer_list
def query_answer(self, answer_id):
"""
:type answer_id:int
:return:
"""
answer = DB.query_row(u'select * from Answer where answer_id in ({answer_id})'.format(answer_id=answer_id))
answer = self.format_answer(answer)
return answer
def extract_topic(self):
raw_topic = DB.query_row(u'select * from Topic where topic_id="{topic_id}"'.format(topic_id=self.task.topic_id))
self.info_page = Topic_Info(raw_topic)
answer_list = self.query_answer_list(self.info_page.best_answer_id_list.split(','))
question_id_dict = OrderedDict()
# 依次获取对应的Question对象
for answer in answer_list:
if answer.question_id not in question_id_dict:
question_id_dict[answer.question_id] = Question(self.query_question(answer.question_id))
question_id_dict[answer.question_id].append_answer(answer)
for question_id in question_id_dict:
self.question_list.append(question_id_dict[question_id])
return
def extract_topic(self):
raw_topic = DB.query_row(u'select * from Topic where topic_id="{topic_id}"'.format(topic_id=self.task.topic_id))
self.info_page = Topic_Info(raw_topic)
answer_list = self.query_answer_list(self.info_page.best_answer_id_list.split(','))
question_id_dict = OrderedDict()
# 依次获取对应的Question对象
for answer in answer_list:
if answer.question_id not in question_id_dict:
question_id_dict[answer.question_id] = Question(self.query_question(answer.question_id))
question_id_dict[answer.question_id].append_answer(answer)
for question_id in question_id_dict:
self.question_list.append(question_id_dict[question_id])
return
def extract_collection(self):
raw_collection = DB.query_row(
u'select * from Collection where collection_id="{collection_id}"'.format(collection_id=self.task.collection_id))
self.info_page = Collection_Info(raw_collection)
answer_list = self.query_answer_list(self.info_page.collected_answer_id_list.split(','))
question_id_dict = OrderedDict()
# 依次获取对应的Question对象
for answer in answer_list:
if answer.question_id not in question_id_dict:
question_id_dict[answer.question_id] = Question(self.query_question(answer.question_id))
question_id_dict[answer.question_id].append_answer(answer)
for question_id in question_id_dict:
self.question_list.append(question_id_dict[question_id])
return
def extract_collection(self):
raw_collection = DB.query_row(
u'select * from Collection where collection_id="{collection_id}"'.format(collection_id=self.task.collection_id))
self.info_page = Collection_Info(raw_collection)
answer_list = self.query_answer_list(self.info_page.collected_answer_id_list.split(','))
question_id_dict = OrderedDict()
# 依次获取对应的Question对象
for answer in answer_list:
if answer.question_id not in question_id_dict:
question_id_dict[answer.question_id] = Question(self.query_question(answer.question_id))
question_id_dict[answer.question_id].append_answer(answer)
for question_id in question_id_dict:
self.question_list.append(question_id_dict[question_id])
return
def extract_author(self):
raw_author = DB.query_row(u'select * from Author where author_page_id="{author_page_id}" '.format(author_page_id=self.task.author_page_id))
self.info_page = Author_Info(raw_author)
answer_list = self.query_answer_list_by_author_page_id(self.info_page.author_page_id)
question_id_dict = OrderedDict()
# 依次获取对应的Question对象
for answer in answer_list:
if answer.question_id not in question_id_dict:
db_question_info = self.query_question(answer.question_id)
if not db_question_info:
# 当返回值为空的时候，直接跳过即可
continue
question_id_dict[answer.question_id] = Question(db_question_info)
question_id_dict[answer.question_id].append_answer(answer)
for question_id in question_id_dict:
self.question_list.append(question_id_dict[question_id])
return
def extract_author(self):
raw_author = DB.query_row(u'select * from Author where author_page_id="{author_page_id}" '.format(author_page_id=self.task.author_page_id))
self.info_page = Author_Info(raw_author)
answer_list = self.query_answer_list_by_author_page_id(self.info_page.author_page_id)
question_id_dict = OrderedDict()
# 依次获取对应的Question对象
for answer in answer_list:
if answer.question_id not in question_id_dict:
db_question_info = self.query_question(answer.question_id)
if not db_question_info:
# 当返回值为空的时候，直接跳过即可
continue
question_id_dict[answer.question_id] = Question(db_question_info)
question_id_dict[answer.question_id].append_answer(answer)
for question_id in question_id_dict:
self.question_list.append(question_id_dict[question_id])
return
def catch(account_id):
# 关键就在这里了
article_url_index_list = []
# 获取最大页码
url = 'http://www.taoguba.com.cn/Article/' + account_id + '/1'
front_page_content = Http.get_content(url)
star_page = 1
with open('ReadList.txt', 'r') as read_list:
read_list = read_list.readlines()
for line in read_list:
if str(line).__contains__('#'):
split_url = line.split('#')[0]
trgId = split_url.split('/')[-2]
if trgId == account_id:
pg = (split_url.split('/')[-1])
print pg
star_page = int(pg)
if star_page == 0:
star_page = 1
else:
print star_page
max_page = 2
dom = BeautifulSoup(front_page_content, "lxml")
list_pcyc_l_ = dom.find_all('div', class_="left t_page01")
try:
for tgo_tgo_ in list_pcyc_l_:
linkl = tgo_tgo_.findAll('a')
tarUrl = linkl[0].get('href')
max_page = int(tarUrl.split('/')[3])
except IndexError as e:
max_page = 1
column_info = TGBColumnParser(front_page_content).get_column_info()
from src.worker import Worker
Worker.save_record_list(u'Column', [column_info])
Debug.logger.info(u"最大页数抓取完毕，共{max_page}页".format(max_page=max_page))
index_work_set = OrderedDict()
# 获取每一页中文章的地址的地址
# star_page = 100
for raw_front_page_index in range(star_page, max_page + 1):
request_url = 'http://www.taoguba.com.cn/Article/' + account_id + '/' + str(
raw_front_page_index)
article_url_index_list.append(request_url)
article_count = len(article_url_index_list)
Debug.logger.info(u"文章链接抓取完毕，共{article_count}篇文章待抓取".format(
article_count=article_count))
index_work_set = OrderedDict()
for article_url_index in article_url_index_list:
print 'query : ' + article_url_index
article_db = DB.query_row(
'select count(*) as article_count from Article where article_id = "{}"'
.format(article_url_index))
if article_db['article_count'] > 0:
continue
request_url = article_url_index
index_work_set[article_url_index] = request_url
re_catch_counter = 0
while len(index_work_set) > 0 and re_catch_counter <= 20:
re_catch_counter += 1
for article_url_index in index_work_set:
request_url = index_work_set[article_url_index]
Debug.logger.info(
u"开始抓取{countert}号文章，剩余{article_count}篇".format(
countert=article_url_index,
article_count=len(index_work_set)))
request_url_content = Http.get_content(request_url)
article_info = TGBArticleParser(
request_url_content).get_article_info()
if len(article_info) > 0:
article_info['article_id'] = article_url_index
article_info['column_id'] = account_id
Worker.save_record_list(u'Article', [article_info])
del index_work_set[article_url_index]
return
def catch(account_id):
# 关键就在这里了
mock_sleep_time = 0.5
base_sleep_time = 1
max_sleep_time = 1
article_url_index_list = []
# 获取最大页码
url = 'http://www.jintiankansha.me/tag/{}?page=1'.format(account_id)
column_info = JinWanKanSaEmptColumnParser('').get_column_info()
column_info[u'column_id'] = account_id
dt = datetime.datetime.now()
column_info[u'title'] = u"AI_{}".format(dt.strftime("%Y-%m-%d"))
max_page = 1
typeToTry = 'tag'
with open('ReadList.txt', 'r') as read_list:
read_list = read_list.readlines()
for line in read_list:
split_url = line.split('#')[0]
if split_url.split('/')[-1] == account_id:
dt = datetime.datetime.now()
column_info[u'title'] = u"{}_{}".format(
line.split('#')[1], dt.strftime("%Y-%m-%d"))
max_page = int(line.split('#')[2])
typeToTry = str(int(line.split('#')[-1])).strip('\n')
from src.worker import Worker
Worker.save_record_list(u'Column', [column_info])
Debug.logger.info(u"最大页数抓取完毕，共{max_page}页".format(max_page=max_page))
index_work_set = OrderedDict()
# 获取每一页中文章的地址的地址
for raw_front_page_index in range(0, max_page + 1):
# request_url = u'http://www.jintiankansha.me/column/{}?page={}'.format(account_id, raw_front_page_index)
request_url = u'http://www.jintiankansha.me/{}/{}?page={}'.format(
typeToTry, account_id, raw_front_page_index)
print request_url
index_work_set[raw_front_page_index] = request_url
re_catch_counter = 0
catch_counter = 0
while len(index_work_set) > 0 and re_catch_counter <= 20:
re_catch_counter += 1
for raw_front_page_index in index_work_set:
catch_counter += 1
Debug.logger.info(u'第『{}』遍抓取数据'.format(re_catch_counter))
request_url = index_work_set[raw_front_page_index]
Debug.logger.info(
u"开始抓取第{raw_front_page_index}页中的文章链接，剩余{max_page}页".format(
raw_front_page_index=raw_front_page_index,
max_page=len(index_work_set)))
request_url_content = Http.get_content(request_url)
soup = BeautifulSoup(request_url_content, 'html.parser')
list_p_list = soup.find_all('span', class_="item_title")
for tgo_right in list_p_list:
for link in tgo_right.findAll('a'):
ttt = str(link.get('href'))
print ttt
if not (ttt is None):
article_url_index_list.append(ttt)
del index_work_set[raw_front_page_index]
# article_url_index_list.append('http://www.jintiankansha.me/t/u8MygoqKI8')
article_count = len(article_url_index_list)
Debug.logger.info(u"文章链接抓取完毕，共{article_count}篇文章待抓取".format(
article_count=article_count))
index_work_set = OrderedDict()
for article_url_index in article_url_index_list:
print 'query : ' + article_url_index
article_db = DB.query_row(
'select count(*) as article_count from Article where article_id = "{}"'
.format(article_url_index))
if article_db['article_count'] > 0:
continue
request_url = article_url_index
index_work_set[article_url_index] = request_url
re_catch_counter = 0
while len(index_work_set) > 0 and re_catch_counter <= 20:
re_catch_counter += 1
for article_url_index in index_work_set:
request_url = index_work_set[article_url_index]
Debug.logger.info(
u"开始抓取 {countert} 号文章，剩余{article_count}篇".format(
countert=article_url_index,
article_count=len(index_work_set)))
request_url_content = Http.get_content(request_url)
time.sleep(mock_sleep_time)
if len(request_url_content) == 0:
random_sleep_time = base_sleep_time + random.randint(
0, max_sleep_time) / 100.0
Debug.logger.info(u"随机休眠{}秒".format(random_sleep_time))
time.sleep(random_sleep_time)
continue
article_info = JinWanKanSaArticleParser(
request_url_content).get_article_info()
if len(article_info) > 0:
article_info['article_id'] = article_url_index
article_info['column_id'] = account_id
Worker.save_record_list(u'Article', [article_info])
del index_work_set[article_url_index]
return
def catch(account_id):
# 关键就在这里了
mock_sleep_time = 0.5
base_sleep_time = 10
max_sleep_time = 10
article_url_index_list = []
# 获取最大页码
column_info = Todo3ColumnParser('').get_column_info()
column_info[u'column_id'] = account_id
column_info[u'title'] = "新能源汽车"
column_info['article_count'] = 0
column_info['follower_count'] = 0
column_info['description'] = ''
column_info['image_url'] = ''
from src.worker import Worker
Worker.save_record_list(u'Column', [column_info])
star_page = 1
max_page = 1
from src.worker import Worker
Worker.save_record_list(u'Column', [column_info])
Debug.logger.info(u"最大页数抓取完毕，共{max_page}页".format(max_page=max_page))
index_work_set = OrderedDict()
#获取每一页中文章的地址的地址
for raw_front_page_index in range(star_page, max_page):
request_url = u'https://post.smzdm.com/fenlei/xinnengyuanche/p{}/'.format(
raw_front_page_index)
index_work_set[raw_front_page_index] = request_url
re_catch_counter = 0
catch_counter = 0
while len(index_work_set) > 0 and re_catch_counter <= 20:
re_catch_counter += 1
for raw_front_page_index in index_work_set:
catch_counter += 1
Debug.logger.info(u'第『{}』遍抓取数据'.format(re_catch_counter))
request_url = index_work_set[raw_front_page_index]
Debug.logger.info(
u"开始抓取第{raw_front_page_index}页中的文章链接，剩余{max_page}页".format(
raw_front_page_index=raw_front_page_index,
max_page=len(index_work_set)))
request_url_content = Http.get_content(request_url)
soup = BeautifulSoup(request_url_content, 'lxml')
list_p_list = soup.find_all('div',
class_='list-border clearfix')
for p in list_p_list:
# print p
list_pcyc_li = p.find_all('a')
li = list_pcyc_li[0]
tarUrl = li.get('href')
ttt = str(tarUrl).split("#")[-1]
print ttt
if not (ttt is None):
article_url_index_list.append(ttt)
del index_work_set[raw_front_page_index]
article_count = len(article_url_index_list)
Debug.logger.info(u"文章链接抓取完毕，共{article_count}篇文章待抓取".format(
article_count=article_count))
index_work_set = OrderedDict()
for article_url_index in article_url_index_list:
print 'query : ' + article_url_index
article_db = DB.query_row(
'select count(*) as article_count from Article where article_id = "{}"'
.format(article_url_index))
if article_db['article_count'] > 0:
continue
request_url = article_url_index
index_work_set[article_url_index] = request_url
re_catch_counter = 0
while len(index_work_set) > 0 and re_catch_counter <= 20:
re_catch_counter += 1
for article_url_index in index_work_set:
request_url = index_work_set[article_url_index]
Debug.logger.info(
u"开始抓取{countert}号文章，剩余{article_count}篇".format(
countert=article_url_index,
article_count=len(index_work_set)))
request_url_content = Http.get_content(request_url)
article_info = Todo3ArticleParser(
request_url_content).get_article_info()
if len(article_info) > 0:
article_info['article_id'] = article_url_index
article_info['column_id'] = account_id
Worker.save_record_list(u'Article', [article_info])
del index_work_set[article_url_index]
return
def catch(account_id):
# 关键就在这里了
mock_sleep_time = 0.5
base_sleep_time = 10
max_sleep_time = 10
article_url_index_list = []
# 获取最大页码
url = 'https://www.wuxiareview.com/category/{}'.format(account_id)
front_page_content = Http.get_content(url)
column_info = WuXiaColumnParser(front_page_content).get_column_info()
column_info[u'column_id'] = account_id
max_page = 2
if account_id == 'daidai':
column_info[u'title'] = "吃瓜群众岱岱"
max_page = 1
elif account_id == 'gzmdzst':
column_info[u'title'] = "顾子明的政事堂"
max_page = 1
else:
column_info[u'title'] = "时文"
max_page = 2
from src.worker import Worker
Worker.save_record_list(u'Column', [column_info])
Debug.logger.info(u"最大页数抓取完毕，共{max_page}页".format(max_page=max_page))
index_work_set = OrderedDict()
# 获取每一页中文章的地址的地址
for raw_front_page_index in range(0, max_page):
request_url = u'https://www.wuxiareview.com/category/{}/{}/'.format(
account_id, raw_front_page_index)
index_work_set[raw_front_page_index] = request_url
re_catch_counter = 0
catch_counter = 0
while len(index_work_set) > 0 and re_catch_counter <= 20:
re_catch_counter += 1
for raw_front_page_index in index_work_set:
catch_counter += 1
Debug.logger.info(u'第『{}』遍抓取数据'.format(re_catch_counter))
request_url = index_work_set[raw_front_page_index]
Debug.logger.info(
u"开始抓取第{raw_front_page_index}页中的文章链接，剩余{max_page}页".format(
raw_front_page_index=raw_front_page_index,
max_page=len(index_work_set)))
request_url_content = Http.get_content(request_url)
soup = BeautifulSoup(request_url_content, 'lxml')
list_p_list = soup.find_all('article', class_="excerpt")
for p in list_p_list:
# print p
list_pcyc_li = p.find_all('a')
for li in list_pcyc_li:
# print li.text
tarUrl = li.get('href')
ttt = str(tarUrl).split("#")[-1]
print ttt
if not (ttt is None):
article_url_index_list.append(ttt)
del index_work_set[raw_front_page_index]
article_count = len(article_url_index_list)
Debug.logger.info(u"文章链接抓取完毕，共{article_count}篇文章待抓取".format(
article_count=article_count))
index_work_set = OrderedDict()
for article_url_index in article_url_index_list:
print 'query : ' + article_url_index
article_db = DB.query_row(
'select count(*) as article_count from Article where article_id = "{}"'
.format(article_url_index))
if article_db['article_count'] > 0:
continue
request_url = article_url_index
index_work_set[article_url_index] = request_url
re_catch_counter = 0
while len(index_work_set) > 0 and re_catch_counter <= 20:
re_catch_counter += 1
for article_url_index in index_work_set:
request_url = index_work_set[article_url_index]
Debug.logger.info(
u"开始抓取{countert}号文章，剩余{article_count}篇".format(
countert=article_url_index,
article_count=len(index_work_set)))
request_url_content = Http.get_content(request_url)
article_info = WuXiaArticleParser(
request_url_content).get_article_info()
if len(article_info) > 0:
article_info['article_id'] = article_url_index
article_info['column_id'] = account_id
Worker.save_record_list(u'Article', [article_info])
del index_work_set[article_url_index]
return
def catch(account_id):
# 关键就在这里了
mock_sleep_time = 0.5
base_sleep_time = 10
max_sleep_time = 10
article_url_index_list = []
# 获取最大页码
url = 'http://www.gushequ.com/{}/'.format(account_id)
front_page_content = Http.get_content(url)
column_info = TodoColumnParser(front_page_content).get_column_info()
column_info[u'column_id'] = account_id
column_info[u'title'] = "股社区"
from src.worker import Worker
Worker.save_record_list(u'Column', [column_info])
star_page = 0
max_page = 24
if account_id == '2018':
star_page = 0
max_page = 24
elif account_id == '2017':
star_page = 24
max_page = 58
elif account_id == '2016':
star_page = 58
max_page = 92
from src.worker import Worker
Worker.save_record_list(u'Column', [column_info])
Debug.logger.info(u"最大页数抓取完毕，共{max_page}页".format(max_page=max_page))
index_work_set = OrderedDict()
#获取每一页中文章的地址的地址
for raw_front_page_index in range(star_page, max_page):
request_url = u'http://www.gushequ.com/page/{}/'.format(
raw_front_page_index)
index_work_set[raw_front_page_index] = request_url
re_catch_counter = 0
catch_counter = 0
while len(index_work_set) > 0 and re_catch_counter <= 20:
re_catch_counter += 1
for raw_front_page_index in index_work_set:
catch_counter += 1
Debug.logger.info(u'第『{}』遍抓取数据'.format(re_catch_counter))
request_url = index_work_set[raw_front_page_index]
Debug.logger.info(
u"开始抓取第{raw_front_page_index}页中的文章链接，剩余{max_page}页".format(
raw_front_page_index=raw_front_page_index,
max_page=len(index_work_set)))
request_url_content = Http.get_content(request_url)
soup = BeautifulSoup(request_url_content, 'lxml')
list_p_list = soup.find_all('article')
for p in list_p_list:
# print p
list_pcyc_li = p.find_all('a')
for li in list_pcyc_li:
tarUrl = li.get('href')
ttt = str(tarUrl).split("#")[-1]
print ttt
if not (ttt is None):
article_url_index_list.append(ttt)
del index_work_set[raw_front_page_index]
article_count = len(article_url_index_list)
Debug.logger.info(u"文章链接抓取完毕，共{article_count}篇文章待抓取".format(
article_count=article_count))
index_work_set = OrderedDict()
for article_url_index in article_url_index_list:
print 'query : ' + article_url_index
article_db = DB.query_row(
'select count(*) as article_count from Article where article_id = "{}"'
.format(article_url_index))
if article_db['article_count'] > 0:
continue
request_url = article_url_index
index_work_set[article_url_index] = request_url
re_catch_counter = 0
while len(index_work_set) > 0 and re_catch_counter <= 20:
re_catch_counter += 1
for article_url_index in index_work_set:
request_url = index_work_set[article_url_index]
Debug.logger.info(
u"开始抓取{countert}号文章，剩余{article_count}篇".format(
countert=article_url_index,
article_count=len(index_work_set)))
request_url_content = Http.get_content(request_url)
article_info = TodoArticleParser(
request_url_content).get_article_info()
if len(article_info) > 0:
article_info['article_id'] = article_url_index
article_info['column_id'] = account_id
Worker.save_record_list(u'Article', [article_info])
del index_work_set[article_url_index]
return
def query_article(self, article_id):
print u"query_article {}".format(article_id)
raw_article = DB.query_row(u'select * from Article where article_id="{article_id}" '.format(article_id=article_id))
article = self.format_article(raw_article)
return article
def catch(account_id):
# 关键就在这里了
mock_sleep_time = 0.5
base_sleep_time = 10
max_sleep_time = 10
article_url_index_list = []
# 获取最大页码
star_page = 1
max_page = 1
column_info = Todo1ColumnParser("").get_column_info()
column_info[u'column_id'] = account_id
with open('ReadList.txt', 'r') as read_list:
read_list = read_list.readlines()
for line in read_list:
split_url = line.split('#')[0]
if str(split_url).__contains__(account_id):
# Config.now_id_likeName = line.split('#')[1]
max_page = int(line.split('#')[-1]) + 1
column_info[u'title'] = str(line.split('#')[1])
# max_page = 1
print max_page
from src.worker import Worker
Worker.save_record_list(u'Column', [column_info])
from src.worker import Worker
Worker.save_record_list(u'Column', [column_info])
Debug.logger.info(u"最大页数抓取完毕，共{max_page}页".format(max_page=max_page))
index_work_set = OrderedDict()
#获取每一页中文章的地址的地址
for raw_front_page_index in range(star_page, max_page):
request_url = u'https://www.guancha.cn/{}/list_{}.shtml'.format(
account_id, raw_front_page_index)
index_work_set[raw_front_page_index] = request_url
re_catch_counter = 0
catch_counter = 0
while len(index_work_set) > 0 and re_catch_counter <= 20:
re_catch_counter += 1
for raw_front_page_index in index_work_set:
catch_counter += 1
Debug.logger.info(u'第『{}』遍抓取数据'.format(re_catch_counter))
request_url = index_work_set[raw_front_page_index]
Debug.logger.info(
u"开始抓取第{raw_front_page_index}页中的文章链接，剩余{max_page}页".format(
raw_front_page_index=raw_front_page_index,
max_page=len(index_work_set)))
request_url_content = Http.get_content(request_url)
soup = BeautifulSoup(request_url_content, 'lxml')
list_p_list = soup.find_all('h4', class_="module-title")
for p in list_p_list:
# print p
list_pcyc_li = p.find_all('a')
for li in list_pcyc_li:
ttt = li.get('href')
print ttt
if not (ttt is None):
ss = str(ttt).split('.')
article_url_index_list.append(
u"https://www.guancha.cn{}_s.{}".format(
ss[0], ss[1]))
del index_work_set[raw_front_page_index]
article_count = len(article_url_index_list)
Debug.logger.info(u"文章链接抓取完毕，共{article_count}篇文章待抓取".format(
article_count=article_count))
index_work_set = OrderedDict()
for article_url_index in article_url_index_list:
print 'query : ' + article_url_index
article_db = DB.query_row(
'select count(*) as article_count from Article where article_id = "{}"'
.format(article_url_index))
if article_db['article_count'] > 0:
continue
request_url = article_url_index
index_work_set[article_url_index] = request_url
re_catch_counter = 0
while len(index_work_set) > 0 and re_catch_counter <= 20:
re_catch_counter += 1
for article_url_index in index_work_set:
request_url = index_work_set[article_url_index]
Debug.logger.info(
u"开始抓取{countert}号文章，剩余{article_count}篇".format(
countert=article_url_index,
article_count=len(index_work_set)))
request_url_content = Http.get_content(request_url)
article_info = Todo1ArticleParser(
request_url_content).get_article_info()
if len(article_info) > 0:
article_info['article_id'] = article_url_index
article_info['column_id'] = account_id
Worker.save_record_list(u'Article', [article_info])
del index_work_set[article_url_index]
return
def query_column(self, column_id):
raw_column = DB.query_row(u'select * from Column where column_id="{column_id}"'.format(column_id=column_id))
column = self.format_column(raw_column) # 包装成标准的信息格式
return column
def query_column(self, column_id):
raw_column = DB.query_row(u'select * from Column where column_id="{column_id}"'.format(column_id=column_id))
column = self.format_column(raw_column) # 包装成标准的信息格式
return column
def query_article(self, article_id):
raw_article = DB.query_row(u'select * from Article where article_id="{article_id}" '.format(article_id=article_id))
article = self.format_article(raw_article)
return article
def catch(account_id):
# 关键就在这里了
mock_sleep_time = 0.5
base_sleep_time = 10
max_sleep_time = 10
article_url_index_list = []
# 获取最大页码
column_info = Todo2ColumnParser("").get_column_info()
column_info[u'column_id'] = account_id
column_info[u'title'] = "纽约时报"
from src.worker import Worker
Worker.save_record_list(u'Column', [column_info])
star_page = 0
max_page = 0
from src.worker import Worker
Worker.save_record_list(u'Column', [column_info])
Debug.logger.info(u"最大页数抓取完毕，共{max_page}页".format(max_page=max_page))
index_work_set = OrderedDict()
#获取每一页中文章的地址的地址
for raw_front_page_index in range(star_page, max_page):
request_url = u'https://cn.nytimes.com/search/data/?query=DAVID%20BARBOZA&lang=&dt=json&from={}&size=10'.format(
raw_front_page_index * 10)
# request_url = u'https://cn.nytimes.com/real-estate/{}/'.format(raw_front_page_index)
index_work_set[raw_front_page_index] = request_url
re_catch_counter = 0
catch_counter = 0
while len(index_work_set) > 0 and re_catch_counter <= 20:
re_catch_counter += 1
for raw_front_page_index in index_work_set:
catch_counter += 1
Debug.logger.info(u'第『{}』遍抓取数据'.format(re_catch_counter))
request_url = index_work_set[raw_front_page_index]
Debug.logger.info(
u"开始抓取第{raw_front_page_index}页中的文章链接，剩余{max_page}页".format(
raw_front_page_index=raw_front_page_index,
max_page=len(index_work_set)))
content = Http.get_content(request_url)
# json 返回中 url
if not content:
return
jdata = json.loads(content)
articles = jdata['items']
for article in articles:
print article['headline']
uur = article['web_url_with_host']
print uur
article_url_index_list.append(uur)
# soup = BeautifulSoup(content, 'lxml')
# list_p_list = soup.find_all('h3' ,class_="regularSummaryHeadline")
# for p in list_p_list:
# # print p
# list_pcyc_li = p.find_all('a')
# for li in list_pcyc_li:
#
# tarUrl = str(li.get('href'))
# print tarUrl
#
# if not (tarUrl is None):
# if str(tarUrl).__contains__("cn.nytimes.com"):
# article_url_index_list.append(u"https:{}".format(tarUrl))
# else:
# article_url_index_list.append(u"https://cn.nytimes.com{}".format(tarUrl))
del index_work_set[raw_front_page_index]
article_count = len(article_url_index_list)
Debug.logger.info(u"文章链接抓取完毕，共{article_count}篇文章待抓取".format(
article_count=article_count))
index_work_set = OrderedDict()
for article_url_index in article_url_index_list:
print 'query : ' + article_url_index
article_db = DB.query_row(
'select count(*) as article_count from Article where article_id = "{}"'
.format(article_url_index))
if article_db['article_count'] > 0:
continue
request_url = article_url_index
index_work_set[article_url_index] = request_url
re_catch_counter = 0
while len(index_work_set) > 0 and re_catch_counter <= 20:
re_catch_counter += 1
for article_url_index in index_work_set:
request_url = index_work_set[article_url_index]
Debug.logger.info(
u"开始抓取{countert}号文章，剩余{article_count}篇".format(
countert=article_url_index,
article_count=len(index_work_set)))
request_url_content = Http.get_content(request_url)
article_info = Todo2ArticleParser(
request_url_content).get_article_info()
if len(article_info) > 0:
article_info['article_id'] = article_url_index
article_info['column_id'] = account_id
Worker.save_record_list(u'Article', [article_info])
del index_work_set[article_url_index]
return
def catch(account_id):
# 关键就在这里了
mock_sleep_time = 0.5
base_sleep_time = 10
max_sleep_time = 10
article_url_index_list = []
# 获取最大页码
url = 'http://www.360doc.com/userhome/{}'.format(account_id)
front_page_content = Http.get_content(url)
# Config.now_id_likeName = account_id
# Config.save()
column_info = Doc360ColumnParser(front_page_content).get_column_info()
column_info[u'column_id'] = account_id
column_info[u'title'] = "明公"
max_page = 2
# if account_id == 'daidai':
#
# column_info[u'title'] = "吃瓜群众岱岱"
# max_page = 1
# elif account_id == 'gzmdzst':
#
# column_info[u'title'] = "顾子明的政事堂"
# max_page = 1
# else:
#
# column_info[u'title'] = "时文"
# max_page = 1
from src.worker import Worker
Worker.save_record_list(u'Column', [column_info])
Debug.logger.info(u"最大页数抓取完毕，共{max_page}页".format(max_page=max_page))
index_work_set = OrderedDict()
# 获取每一页中文章的地址的地址
for raw_front_page_index in range(0, max_page):
request_url = u"http://www.360doc.com/ajax/getUserArticle.aspx?pagenum=50&curnum={}&icid=13&ishowabstract=null&word=&userid={}&isoriginal=0&_={}"
urequest_url = (request_url.format(raw_front_page_index,
account_id,
int(time.time() * 1000)))
index_work_set[raw_front_page_index] = urequest_url
re_catch_counter = 0
catch_counter = 0
while len(index_work_set) > 0 and re_catch_counter <= 20:
re_catch_counter += 1
for raw_front_page_index in index_work_set:
catch_counter += 1
Debug.logger.info(u'第『{}』遍抓取数据'.format(re_catch_counter))
request_url = index_work_set[raw_front_page_index]
Debug.logger.info(
u"开始抓取第{raw_front_page_index}页中的文章链接，剩余{max_page}页".format(
raw_front_page_index=raw_front_page_index,
max_page=len(index_work_set)))
request_url_content = Http.get_content(request_url)
soup = BeautifulSoup(request_url_content, 'lxml')
list_p_list = soup.find_all('div',
class_="list listwz1 font14")
for p in list_p_list:
# print p
list_pcyc_li = p.find_all('a')
for li in list_pcyc_li:
# print li.text
tarUrl = li.get('href')
# deep level
print tarUrl
article_url_index_list.append(tarUrl)
del index_work_set[raw_front_page_index]
article_count = len(article_url_index_list)
Debug.logger.info(u"文章链接抓取完毕，共{article_count}篇文章待抓取".format(
article_count=article_count))
index_work_set = OrderedDict()
for article_url_index in article_url_index_list:
print 'query : ' + article_url_index
article_db = DB.query_row(
'select count(*) as article_count from Article where article_id = "{}"'
.format(article_url_index))
if article_db['article_count'] > 0:
continue
request_url = article_url_index
index_work_set[article_url_index] = request_url
re_catch_counter = 0
while len(index_work_set) > 0 and re_catch_counter <= 20:
re_catch_counter += 1
for article_url_index in index_work_set:
request_url = index_work_set[article_url_index]
Debug.logger.info(
u"开始抓取{countert}号文章，剩余{article_count}篇".format(
countert=article_url_index,
article_count=len(index_work_set)))
request_url_content = Http.get_content(request_url)
article_info = Doc360ArticleParser(
request_url_content).get_article_info()
if len(article_info) > 0:
article_info['article_id'] = article_url_index
article_info['column_id'] = account_id
Worker.save_record_list(u'Article', [article_info])
del index_work_set[article_url_index]
return
def catch(account_id):
# 关键就在这里了
mock_sleep_time = 0.5
base_sleep_time = 1
max_sleep_time = 1
article_url_index_list = []
# 获取最大页码
column_info = WeiXinColumnParser('').get_column_info()
column_info[u'column_id'] = account_id
column_info[u'title'] = account_id
column_info[u'image_url'] = 'https://wpimg.wallstcn.com/3598b719-ab0d-4be7-bc09-30c3ae29a3cc.jpg?imageView2/1/w/240/h/240'
max_page = 1
# with open('ReadList.txt', 'r') as read_list:
# read_list = read_list.readlines()
# for line in read_list:
# split_url = line.split('#')[0]
# if str(split_url).__contains__(account_id):
# # Config.now_id_likeName = line.split('#')[1]
# max_page = int(line.split('#')[-1]) + 1
# column_info[u'title'] = str(line.split('#')[1])
#
# # max_page = 1
# print max_page
from src.worker import Worker
Worker.save_record_list(u'Column', [column_info])
Debug.logger.info(u"最大页数抓取完毕，共{max_page}页".format(max_page=max_page))
# article_url_index_list.append('https://mp.weixin.qq.com/s?__biz=MjM5MjczNDc0Mw==&mid=2650847984&idx=2&sn=b7b111e5964d2f2fb568ba0d419e3edf&chksm=bd55d1888a22589e2f3bab0613b346427079efc6b82fac869d4f78244a500c3e5cc8cb8402ed&scene=21#wechat_redirect')
# article_url_index_list.append('https://mp.weixin.qq.com/s/yj1BT3jWyxLjlEnzz0vEtQ')
with open('/Users/0/Desktop/list.txt', 'r') as read_list:
read_list = read_list.readlines()
for line in read_list:
article_url_index_list.append(str(line).strip('\n'))
article_count = len(article_url_index_list)
Debug.logger.info(u"文章链接抓取完毕，共{article_count}篇文章待抓取".format(article_count=article_count))
index_work_set = OrderedDict()
for article_url_index in article_url_index_list:
print 'query : ' + article_url_index
article_db = DB.query_row(
'select count(*) as article_count from Article where article_id = "{}"'.format(article_url_index))
if article_db['article_count'] > 0:
continue
request_url = article_url_index
index_work_set[article_url_index] = request_url
re_catch_counter = 0
while len(index_work_set) > 0 and re_catch_counter <= 20:
re_catch_counter += 1
for article_url_index in index_work_set:
request_url = index_work_set[article_url_index]
Debug.logger.info(u"开始抓取 {countert} 号文章，剩余{article_count}篇".format(countert=article_url_index,
article_count=len(index_work_set)))
request_url_content = Http.get_content(request_url)
time.sleep(mock_sleep_time)
if len(request_url_content) == 0:
random_sleep_time = base_sleep_time + random.randint(0, max_sleep_time) / 100.0
Debug.logger.info(u"随机休眠{}秒".format(random_sleep_time))
time.sleep(random_sleep_time)
continue
#article_info = Todo2ArticleParser(request_url_content).get_article_info()
# article_info = HuXiuArticleParser(request_url_content).get_article_info()
article_info = WeiXinArticleParser(request_url_content).get_article_info()
# article_info = WallStreetArticleParser(request_url_content).get_article_info()
if len(article_info) > 0:
article_info['article_id'] = article_url_index
article_info['column_id'] = account_id
Worker.save_record_list(u'Article', [article_info])
del index_work_set[article_url_index]
return
def catch(account_id):
# 关键就在这里了
mock_sleep_time = 0.5
base_sleep_time = 10
max_sleep_time = 10
article_url_index_list = []
#
url = 'http://xinsheng.huawei.com/{}'.format(account_id)
front_page_content = Http.get_content(url)
column_info = HuaWeiColumnParser(front_page_content).get_column_info()
column_info[u'column_id'] = account_id
column_info[u'title'] = "华为家事"
column_info[
u'image_url'] = 'file:///Users/ex-liyan010/Desktop/share/hcover.jpeg'
from src.worker import Worker
Worker.save_record_list(u'Column', [column_info])
max_page = 0
Debug.logger.info(u"最大页数抓取完毕，共{max_page}页".format(max_page=max_page))
index_work_set = OrderedDict()
# 获取每一页中文章的地址的地址
for raw_front_page_index in range(0, max_page):
request_url = u'http://xinsheng.huawei.com/cn/index.php?app=forum&mod=List&act=index&class=461&order=cTime&type=&sign=&special=&cate=155&p={}'.format(
raw_front_page_index)
index_work_set[raw_front_page_index] = request_url
re_catch_counter = 0
catch_counter = 0
while len(index_work_set) > 0 and re_catch_counter <= 20:
re_catch_counter += 1
for raw_front_page_index in index_work_set:
catch_counter += 1
Debug.logger.info(u'第『{}』遍抓取数据'.format(re_catch_counter))
request_url = index_work_set[raw_front_page_index]
Debug.logger.info(
u"开始抓取第{raw_front_page_index}页中的文章链接，剩余{max_page}页".format(
raw_front_page_index=raw_front_page_index,
max_page=len(index_work_set)))
request_url_content = Http.get_content(request_url)
soup = BeautifulSoup(request_url_content, "lxml")
content_dom = soup.find_all('div', class_="bbs_list")[0]
# print content_dom.text
# t_dom = dom.find_all('tbody')
# # print t_dom
font_box_dom = content_dom.find_all('div', class_="font_box")
# print time_dom
for xx in font_box_dom:
linkl = xx.findAll('a')
tarUrl = linkl[0].get('href')
print tarUrl
article_url_index_list.append(tarUrl)
del index_work_set[raw_front_page_index]
article_url_index_list.append(
'http://xinsheng.huawei.com/cn/index.php?app=forum&mod=Detail&act=index&id=4343641'
)
article_url_index_list.append(
'http://xinsheng.huawei.com/cn/index.php?app=forum&mod=Detail&act=index&id=4340813'
)
article_url_index_list.append(
'http://xinsheng.huawei.com/cn/index.php?app=group&mod=Bbs&act=detail&tid=4346331'
)
article_url_index_list.append(
'http://xinsheng.huawei.com/cn/index.php?app=group&mod=Bbs&act=detail&tid=4347493'
)
article_url_index_list.append(
'http://xinsheng.huawei.com/cn/index.php?app=group&mod=Bbs&act=detail&tid=4342141'
)
article_count = len(article_url_index_list)
Debug.logger.info(u"文章链接抓取完毕，共{article_count}篇文章待抓取".format(
article_count=article_count))
index_work_set = OrderedDict()
for article_url_index in article_url_index_list:
print 'query : ' + article_url_index
article_db = DB.query_row(
'select count(*) as article_count from Article where article_id = "{}"'
.format(article_url_index))
if article_db['article_count'] > 0:
continue
request_url = article_url_index
index_work_set[article_url_index] = request_url
re_catch_counter = 0
while len(index_work_set) > 0 and re_catch_counter <= 20:
re_catch_counter += 1
for article_url_index in index_work_set:
request_url = index_work_set[article_url_index]
Debug.logger.info(
u"开始抓取{countert}号文章，剩余{article_count}篇".format(
countert=article_url_index,
article_count=len(index_work_set)))
request_url_content = Http.get_content(request_url)
article_info = HuaWeiArticleParser(
request_url_content).get_article_info()
if len(article_info) > 0:
article_info['article_id'] = article_url_index
article_info['column_id'] = account_id
Worker.save_record_list(u'Article', [article_info])
del index_work_set[article_url_index]
return
def catch(account_id):
# 关键就在这里了
mock_sleep_time = 0.5
base_sleep_time = 10
max_sleep_time = 10
article_url_index_list = []
# 获取最大页码
url = 'https://www.huxiu.com/{}'.format(account_id)
front_page_content = Http.get_content(url)
# Config.now_id_likeName = account_id
# Config.save()
column_info = HuXiuColumnParser(front_page_content).get_column_info()
column_info[u'column_id'] = account_id
column_info[u'title'] = account_id
from src.worker import Worker
Worker.save_record_list(u'Column', [column_info])
u_result = urllib.quote(
account_id.decode(sys.stdin.encoding).encode('utf8'))
print account_id
max_page = 2
idds = ''
#
with open('ReadList.txt', 'r') as read_list:
read_list = read_list.readlines()
for line in read_list:
split_url = line.split('#')[0]
if split_url.split('/')[-1] == account_id:
# Config.now_id_likeName = line.split('#')[1]
max_page = int(line.split('#')[-1]) + 1
idds = str(line.split('#')[1])
print max_page
max_page = -1
# 分析网页内容，存到数据库里
Debug.logger.info(u"最大页数抓取完毕，共{max_page}页".format(max_page=max_page))
index_work_set = OrderedDict()
# 获取每一页中文章的地址的地址
for raw_front_page_index in range(0, max_page + 1):
#https://www.huxiu.com/search.html?s=%E5%B7%B4%E8%8F%B2%E7%89%B9&sort=dateline:desc
request_url = u'https://www.huxiu.com/search.html?s={}&sort=dateline%3Adesc&per_page={}'.format(
u_result, raw_front_page_index)
#request_url = u'https://www.huxiu.com/member/{}/article/{}.html'.format(idds,raw_front_page_index)
# request_url = 'https://www.huxiu.com/member/1872007.html'
index_work_set[raw_front_page_index] = request_url
re_catch_counter = 0
catch_counter = 0
while len(index_work_set) > 0 and re_catch_counter <= 20:
re_catch_counter += 1
for raw_front_page_index in index_work_set:
catch_counter += 1
Debug.logger.info(u'第『{}』遍抓取数据'.format(re_catch_counter))
request_url = index_work_set[raw_front_page_index]
Debug.logger.info(
u"开始抓取第{raw_front_page_index}页中的文章链接，剩余{max_page}页".format(
raw_front_page_index=raw_front_page_index,
max_page=len(index_work_set)))
request_url_content = Http.get_content(request_url)
soup = BeautifulSoup(request_url_content, "lxml")
list_pcyc_l_ = soup.find_all('li')
# list_pcyc_l_ = soup.find_all('div',class_='mob-ctt')
for tgo_right in list_pcyc_l_:
for link in tgo_right.findAll('a'):
hre = str(link.get('href'))
if hre.startswith('/article/', 0, 10):
print u'https://www.huxiu.com{}'.format(
link.get('href'))
article_url_index_list.append(
'https://www.huxiu.com{}'.format(
link.get('href')))
del index_work_set[raw_front_page_index]
article_url_index_list.append(
'https://www.huxiu.com/article/299355.html')
article_count = len(article_url_index_list)
Debug.logger.info(u"文章链接抓取完毕，共{article_count}篇文章待抓取".format(
article_count=article_count))
index_work_set = OrderedDict()
for article_url_index in article_url_index_list:
print 'query : ' + article_url_index
article_db = DB.query_row(
'select count(*) as article_count from Article where article_id = "{}"'
.format(article_url_index))
if article_db['article_count'] > 0:
continue
request_url = article_url_index
index_work_set[article_url_index] = request_url
re_catch_counter = 0
while len(index_work_set) > 0 and re_catch_counter <= 20:
re_catch_counter += 1
for article_url_index in index_work_set:
request_url = index_work_set[article_url_index]
Debug.logger.info(
u"开始抓取{countert}号文章，剩余{article_count}篇".format(
countert=article_url_index,
article_count=len(index_work_set)))
request_url_content = Http.get_content(request_url)
article_info = HuXiuArticleParser(
request_url_content).get_article_info()
if len(article_info) > 0:
article_info['article_id'] = article_url_index
article_info['column_id'] = account_id
Worker.save_record_list(u'Article', [article_info])
del index_work_set[article_url_index]
return
def catch(account_id):
# 关键就在这里了
mock_sleep_time = 28
base_sleep_time = 62
max_sleep_time = 80
article_url_index_list =[]
# 获取最大页码
url = 'http://chuansong.me/account/{}'.format(account_id)
# front_page_content = Http.get_content(url)
front_page_content =''
# max_page =WechatWorker.parse_max_page(front_page_content)
# if max_page > 200:
# max_page =200
max_page = 0
# 分析网页内容，存到数据库里
column_info = WechatColumnParser(front_page_content).get_column_info()
column_info[u'column_id'] = account_id
with open('ReadList.txt', 'r') as read_list:
read_list = read_list.readlines()
for line in read_list:
split_url = line.split('#')[0]
if str(split_url).__contains__(account_id):
column_info[u'title'] = str(line.split('#')[1])
from src.worker import Worker
Worker.save_record_list(u'Column', [column_info])
Debug.logger.info(u"最大页数抓取完毕，共{max_page}页".format(max_page=max_page))
index_work_set = OrderedDict()
# 获取每一页中文章的地址的地址
for raw_front_page_index in range(0, max_page):
front_page_index = raw_front_page_index * 12
request_url = url + '?start={}'.format(front_page_index)
index_work_set[raw_front_page_index] = request_url
re_catch_counter = 0
catch_counter = 0
while len(index_work_set) > 0 and re_catch_counter <= 20:
re_catch_counter += 1
for raw_front_page_index in index_work_set:
catch_counter += 1
Debug.logger.info(u'第『{}』遍抓取数据'.format(re_catch_counter))
request_url = index_work_set[raw_front_page_index]
Debug.logger.info(
u"开始抓取第{raw_front_page_index}页中的文章链接，剩余{max_page}页".format(raw_front_page_index=raw_front_page_index, max_page=len(index_work_set)))
request_url_content = Http.get_content(request_url)
time.sleep(mock_sleep_time)
if len(request_url_content) == 0 or catch_counter % 5 == 0:
random_sleep_time = base_sleep_time + random.randint(0, max_sleep_time) / 100.0
Debug.logger.info(u"随机休眠{}秒".format(random_sleep_time))
time.sleep(random_sleep_time)
continue
random_sleep_time = base_sleep_time + random.randint(0, max_sleep_time) / 10.0
Debug.logger.info(u"随机休眠{}秒".format(random_sleep_time))
time.sleep(random_sleep_time)
article_url_index_list += Match.wechat_article_index(content=request_url_content)
del index_work_set[raw_front_page_index]
article_count = len(article_url_index_list)
Debug.logger.info(u"文章链接抓取完毕，共{article_count}篇文章待抓取".format(article_count=article_count))
index_work_set = OrderedDict()
for article_url_index in article_url_index_list:
article_db = DB.query_row('select count(*) as article_count from Article where article_id = {}'.format(article_url_index))
if article_db['article_count'] > 0:
continue
request_url = 'http://chuansong.me/n/{}'.format(article_url_index)
index_work_set[article_url_index] = request_url
re_catch_counter = 0
while len(index_work_set) > 0 and re_catch_counter <= 20:
re_catch_counter += 1
for article_url_index in index_work_set:
request_url = index_work_set[article_url_index]
Debug.logger.info(u"开始抓取{countert}号文章，剩余{article_count}篇".format(countert=article_url_index,
article_count=len(index_work_set)))
request_url_content = Http.get_content(request_url)
time.sleep(mock_sleep_time)
if len(request_url_content) == 0:
random_sleep_time = base_sleep_time + random.randint(0, max_sleep_time) / 100.0
Debug.logger.info(u"随机休眠{}秒".format(random_sleep_time))
time.sleep(random_sleep_time)
continue
random_sleep_time = base_sleep_time + random.randint(0, max_sleep_time) / 10.0
Debug.logger.info(u"随机休眠{}秒".format(random_sleep_time))
time.sleep(random_sleep_time)
article_info = WechatArticleParser(request_url_content).get_article_info()
if len(article_info) > 0:
article_info['article_id'] = article_url_index
article_info['column_id'] = account_id
Worker.save_record_list(u'Article', [article_info])
del index_work_set[article_url_index]
return
