int open_log_file(const char *file)
{
if (NULL == file || strlen(file) == 0)
{
return -1;
}
int fd = open(file, O_CREAT | O_WRONLY | O_APPEND, 0640);
if (fd < 0)
{
char file_tmp[1024] = {0};
strncpy(file_tmp, file, 1024);
char *dir = strrchr(file_tmp, '/');
if (NULL == dir)
{
printf("the file must be a dir\n");
return -1;
}
//the dir path may be lost
*dir = '\0';
if (0 == make_dir_recusive(file_tmp, 0644))
{
printf("the mkdir recursive failed, the dir is %s\n", dir);
return -1;
}
fd = open(file, O_CREAT | O_WRONLY | O_APPEND, 0640);
}
if (fd < 0)
{
return -1;
}
//release old log file handler
if (log_file > 0)
{
close(log_file);
}
log_file = fd;
log_fd_invalid = 0;
return 0;
}
bool parse_course_assignment(CURL *curl_web_handler,char *path, p_assignment_element head)
{
extern cache_memory cache;
p_list_entity entity_head = NULL;
entity_head = basic_parse_page(cache.mem,"<tr class=\"tr","</tr>");
// for loop
p_list_entity p = entity_head->next;
reset_cache_memory();
p_assignment_element pre = head;
p_assignment_element cur = head->next;
char buf[BUFFER_MAX_SIZE];
while(p)
{
cur = (p_assignment_element)malloc(sizeof(assignment_element));
// init all char *
init_assignment_element(cur);
char *src = p->entity;
// GET NAME
extract_content_between_tags(p->entity, buf, "<a href","</a>");
remove_and_convert_html(buf);
string_trip(buf);
cur->assignment_name = strdup(buf);
// GET DETAIL URL
extract_content_between_fix(p->entity, buf, "href=\"","\">");
str_add_prefix(HOMEWORK_URL_PREFIX,buf);
// GET DETAIL
get_assignment_detail(curl_web_handler,buf,cur);
// GET TIME
src = extract_content_between_fix( src, buf, "<td width=\"10%\">", "</td>");
cur->assignment_time = strdup(buf);
// GET DEADLINE
src = extract_content_between_fix(src, buf, "<td width=\"10%\">", "</td>");
cur->assignment_deadline = strdup(buf);
// GET STAUTS
src = extract_content_between_tags(src, buf, "<td width=\"15%\"", "</td>");
if(string_trip(buf))
{
cur->assignment_status = strdup(buf);
}
// GET SCORE URL
src = extract_content_between_fix (src, buf, "javascript:window.location.href='","';");
extract_content_between_fix (src, buf,"javascript:window.location.href='","'\"");
if(str_add_prefix(HOMEWORK_URL_PREFIX, buf))
get_assignment_score(curl_web_handler,buf,cur);
//print_assignment_element(cur);
// save it
if(cur->assignment_attachment_url)
{
sprintf(buf,"%s%c%s%c%s%c",path, PATH_SPILIT_CHAR, cur->assignment_name, PATH_SPILIT_CHAR, "教师作业附件", PATH_SPILIT_CHAR);
make_dir_recusive(buf);
sprintf(buf, "%s%s", buf, cur->assignment_attachment_name);
cur->assignment_attachment_location = strdup(buf);
download_file(curl_web_handler,cur->assignment_attachment_url, cur->assignment_attachment_location);
}
if(cur->my_handin_attachment_url)
{
sprintf(buf,"%s%c%s%c%s%c",path, PATH_SPILIT_CHAR, cur->assignment_name, PATH_SPILIT_CHAR, "我的提交", PATH_SPILIT_CHAR);
make_dir_recusive(buf);
sprintf(buf, "%s%s", buf, cur->my_handin_attachment_name);
cur->my_handin_attachment_location = strdup(buf);
download_file(curl_web_handler,cur->my_handin_attachment_url, cur->my_handin_attachment_location);
}
pre->next = cur;
pre = cur;
cur = NULL;
p = p->next;
}
sprintf(buf, "%s%c%s", path, PATH_SPILIT_CHAR, "assignment.xml");
write_all_assignment_to_xmlfile(buf,head);
if(!destroy_all_entity_memory(entity_head))
return FALSE;
if(!destroy_all_assignment_element(head))
return FALSE;
return TRUE;
}
// Get discussion list, main function
bool parse_course_discussion(CURL *curl_web_handler,char *path, p_discussion_element head)
{
extern cache_memory cache;
// split the memory and copy it into entity list
p_list_entity entity_head = NULL;
entity_head = basic_parse_page(cache.mem,"<tr class=\"tr","</tr>");
// for loop
p_list_entity p = entity_head->next;
// reset cache memory and waiting for next download.
reset_cache_memory();
// init
p_discussion_element pre = head;
p_discussion_element cur = head->next;
// BUFFER
char buf[BUFFER_MAX_SIZE];
char num_buf[16];
// loop
char *reply_url = NULL;
//
int discussion_id = 0;
while(p)
{
cur = (p_discussion_element)malloc(sizeof(discussion_element));
// clear cur pointer memory
init_discussion_element(cur);
cur->id = discussion_id;
// save a char pointer and move it, for performance
char *src = p->entity;
// GET TOPIC
extract_content_between_tags(p->entity, buf,"<a href","</a>");
remove_and_convert_html(buf);
cur->discussion_topic = strdup(buf);
// GET REPLY URL WAITING, SAVE IT
extract_content_between_fix(p->entity, buf, "href='","'>");
str_add_prefix(REPLY_URL_PREFIX, buf);
reply_url = strdup(buf);
// GET AUTHOR
src = extract_content_between_tags( src, buf, "<td width=\"15%\"", "</td>");
cur->discussion_author = strdup(buf);
// GET reply and click
src = extract_content_between_fix( src, buf, "<td width=\"15%\">", "</td>");
memset (num_buf, 0, 16);
int i = 0,j = 0;
for(i = 0;i < strlen(buf); i++)
{
if(buf[i] == '/')
{
// how many reply
cur->discussion_reply = atoi(num_buf);
break;
}
num_buf[j++] = buf[i];
}
cur->discussion_click = atoi(buf+i+1);
// Get handin time
extract_content_between_fix(src, buf, "<td width=\"20%\">", "</td>");
cur->discussion_handin_time = strdup(buf);
// Get content...etc
if(!get_reply(curl_web_handler,reply_url, cur))
printf("Get Reply Error, Check Network.\n");
// print
//print_discussion_element(cur);
// write to file
if(cur->discussion_attachment_url)
{
sprintf(buf,"%s%c%d%c%s%c",path, PATH_SPILIT_CHAR,cur->id, PATH_SPILIT_CHAR, "附件", PATH_SPILIT_CHAR);
make_dir_recusive(buf);
sprintf(buf, "%s%s", buf, cur->discussion_attachment_name);
cur->discussion_attachment_location = strdup(buf);
download_file(curl_web_handler,cur->discussion_attachment_url, cur->discussion_attachment_location);
}
if(cur->reply_head)
{
sprintf(buf,"%s%c%d%c%s%c",path, PATH_SPILIT_CHAR, cur->id, PATH_SPILIT_CHAR, "回复附件", PATH_SPILIT_CHAR);
download_reply_attachment(curl_web_handler,buf, cur->reply_head);
}
pre->next = cur;
pre = cur;
cur = NULL;
p = p->next;
discussion_id ++;
}
sprintf(buf, "%s%c%s", path, PATH_SPILIT_CHAR, "discussion.xml");
write_all_discussion_to_xmlfile(buf,head);
if(!destroy_all_entity_memory (entity_head))
return FALSE;
if(!destroy_all_discussion_element (head))
return FALSE;
return TRUE;
}
bool parse_course_file(CURL *curl_web_handler,char *path,p_file_element head)
{
extern cache_memory cache;
// temp buffer
char buf[BUFFER_MAX_SIZE];
memset(buf, 0 ,BUFFER_MAX_SIZE);
// saved the file type name
char file_type_name[6][128];
// how many of types
int i = 0;
int no_of_file_type = 0;
// pointer to the cache.
char *p_cache = cache.mem;
for(i = 0;i < 5; i++)
{
memset(file_type_name[i], 0, 128);
p_cache = extract_content_between_tags(p_cache,file_type_name[i],"<td class=\"textTD\"","</td>");
if(!p_cache)
break;
}
no_of_file_type = i;
p_cache = cache.mem;
char *p_cache_start[6];
p_cache_start[0] = p_cache;
// discard p_cache_start[0], it has no use.
for(i = 1; i<= no_of_file_type;i++)
{
p_cache_start[i] = strstr(p_cache_start[i-1] + 1, "<table id=\"table_box\"");
memset(p_cache_start[i] - 1, 0, 1);
}
// because 0 not use.
p_file_element pre = head;
p_file_element cur = head->next;
for(i = 1;i <= no_of_file_type;i++)
{
char file_save_prefix[BUFFER_MAX_SIZE];
sprintf(file_save_prefix, "%s%c%s%c",path, PATH_SPILIT_CHAR,file_type_name[i-1],PATH_SPILIT_CHAR);
make_dir_recusive(file_save_prefix);
p_list_entity entity_head = NULL;
entity_head = basic_parse_page(p_cache_start[i],"<tr class=\"tr","</tr>");
// for loop
p_list_entity p = entity_head->next;
while(p)
{
cur = (p_file_element)malloc(sizeof(file_element));
if(!init_file_element(cur))
{
printf("Init Error!\n");
return FALSE;
}
// SET FILE TYPE
cur->file_type = strdup(file_type_name[i-1]);
// SET DOCUMENT ID
char *pointer_src = p->entity;
pointer_src = extract_content_between_tags(pointer_src, buf, "<td width=\"80\">","</td>");
cur->file_id = atoi(buf);
// GET DOCUMENT ORIGIN_NAME
pointer_src = extract_content_between_fix(pointer_src, buf, "getfilelink=", "&");
cur->file_orign_name = strdup(buf);
// GET FILE URL
extract_content_between_fix(pointer_src, buf, "href=\"","\" >");
str_add_prefix(tsinghua_prefix,buf);
cur->file_url = strdup(buf);
// GET FILE TITLE && MOVE POINTER
pointer_src = extract_content_between_tags(pointer_src, buf, "<a target=\"_top\"", "</a>");
remove_and_convert_html(buf);
if(string_trip(buf))
{
remove_path_spilit_char(buf);
cur->file_title = strdup(buf);
}
else
cur->file_title = NULL;
// GET FILE ABSTRACT
pointer_src = extract_content_between_tags(pointer_src, buf, "<td width=\"300\"", "</td>");
cur->file_abstract = strdup(buf);
// GET FILE UP TIME
pointer_src = extract_content_between_tags(pointer_src, buf, "<td width=\"100\"", "</td>");
cur->file_up_time = strdup(buf);
sprintf(buf, "%s%s_%s",file_save_prefix,cur->file_title,cur->file_orign_name);
cur->file_local_location = strdup(buf);
download_file(curl_web_handler,cur->file_url, cur->file_local_location);
//print_file_element(cur);
pre->next = cur;
pre = cur;
cur = NULL;
p = p->next;
}
if( !destroy_all_entity_memory(entity_head))
{
printf("FREE EROOR @ LINE %d FILE %s",__LINE__, __FILE__);
return FALSE;
}
}
reset_cache_memory();
sprintf(buf, "%s%c%s",path, PATH_SPILIT_CHAR,"file.xml");
write_all_file_to_xmlfile(buf,head);
if(!destroy_all_file_element(head))
{
printf("FREE EROOR @ LINE %d FILE %s",__LINE__, __FILE__);
return FALSE;
}
return TRUE;
}
